© 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. 113514
    Prev
    Next
    INDEX
    Explanations

    axon terminals and growth factors

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

    biochemical terms and proteins like "auxin," "axon," "leptin," and "transcription factors."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    the
    -2.36
    ll
    -2.08
    //
    -2.06
    >
    -1.99
    "
    -1.98
    *
    -1.95
    over
    -1.95
    ']>
    -1.91
    a
    -1.91
    <blockquote>
    -1.91
    POSITIVE LOGITS
     帅气
    2.16
     has
    2.03
     Añade
    1.97
     certaines
    1.96
     chiesto
    1.95
     trovato
    1.93
     son
    1.92
     dovuto
    1.91
     provato
    1.88
     antiguas
    1.86
    Activations Density 0.030%

    No Known Activations