© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72315
    Prev
    Next
    INDEX
    Explanations

    upcoming projects

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron predominantly activates on common function words (e.g. articles, conjunctions, and prepositions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    text describing current or ongoing creative/professional projects and

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of ongoing or upcoming creative projects and activities—especially in music—such as working on new material, planning releases, and preparing shows.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baca
    -1.19
     from
    -1.16
     it
    -1.15
    當時
    -1.13
     how
    -1.04
     system
    -1.00
     through
    -0.99
     could
    -0.99
     when
    -0.98
     at
    -0.96
    POSITIVE LOGITS
     projects
    1.51
     upcoming
    1.39
     next
    1.32
     prossima
    1.24
     Estamos
    1.23
     Etapa
    1.23
     frattempo
    1.23
     капю
    1.22
    gernaut
    1.21
    projek
    1.18
    Activations Density 0.020%

    No Known Activations