© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72640
    Prev
    Next
    INDEX
    Explanations

    numbers indicating a limit

    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
    essentially
    -1.78
    the
    -1.73
    และ
    -1.73
    and
    -1.70
     gena
    -1.62
    .
    -1.55
    m
    -1.52
    졍
    -1.52
     vaste
    -1.51
    basically
    -1.51
    POSITIVE LOGITS
     of
    2.69
     zelfs
    2.22
     even
    2.11
     where
    1.92
     this
    1.82
     sogar
    1.73
     on
    1.72
     if
    1.63
     from
    1.63
     use
    1.61
    Activations Density 0.042%

    No Known Activations