© 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. 14728
    Prev
    Next
    INDEX
    Explanations

    explaining things or asking questions

    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_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
     is
    -2.50
     также
    -1.90
    話は
    -1.58
    Additionally
    -1.58
    >
    -1.57
    凄く
    -1.55
    还未
    -1.54
     myös
    -1.53
    絶対に
    -1.53
    是一个
    -1.52
    POSITIVE LOGITS
     then
    3.20
     that
    2.69
     what
    2.09
     how
    2.08
     when
    2.06
     or
    1.99
     to
    1.91
     why
    1.84
     where
    1.71
    倨
    1.67
    Activations Density 0.033%

    No Known Activations