© 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. 34-GEMMASCOPE-RES-131K
    7. 30580
    Prev
    Next
    INDEX
    Explanations

    front parts of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     backend
    -1.09
     nearby
    -1.03
    frontend
    -0.98
     southwestern
    -0.96
     outback
    -0.94
     avviene
    -0.94
     語
    -0.93
     backstage
    -0.93
     downtown
    -0.92
     okol
    -0.90
    POSITIVE LOGITS
     of
    1.03
    のみ
    0.93
     quando
    0.92
     و
    0.91
    景色
    0.91
     и
    0.88
    蜃
    0.85
     habitual
    0.83
    <bos>
    0.82
     Vicky
    0.82
    Activations Density 0.114%

    No Known Activations