© 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. 10-GEMMASCOPE-RES-131K
    7. 45231
    Prev
    Next
    INDEX
    Explanations

    may have

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

    The neuron fires on words and phrases that describe outcomes, effects, or lessons being caused or experienced.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     a
    -1.70
     for
    -1.34
     like
    -1.32
    一個
    -1.23
     emosi
    -1.20
     so
    -1.15
    一个
    -1.13
     an
    -1.12
     something
    -1.05
     Sean
    -1.05
    POSITIVE LOGITS
     pueda
    1.32
     יכול
    1.25
     možno
    1.20
     they
    1.18
     possibilité
    1.16
     dalších
    1.15
     varje
    1.15
    CARACTERIST
    1.13
     may
    1.11
     mungkin
    1.11
    Activations Density 0.098%

    No Known Activations