© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39150
    Prev
    Next
    INDEX
    Explanations

    often times

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

    The neuron is detecting formal academic or scholarly language—specifically high-register, multisyllabic content words and jargon typical of theoretical or philosophical writing.

    oai_token-act-pair · o4-miniTriggered 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
     bahay
    -1.47
     postale
    -1.39
    ţiei
    -1.38
    adomo
    -1.38
    很赞
    -1.37
     alemania
    -1.31
     diing
    -1.29
     lucu
    -1.27
     mentioned
    -1.27
     広場
    -1.26
    POSITIVE LOGITS
     our
    1.75
     Our
    1.30
     my
    1.23
     we
    1.16
     I
    1.16
     That
    1.14
    !
    1.13
     иногда
    1.11
     k
    1.10
     bizim
    1.09
    Activations Density 0.057%

    No Known Activations