© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    introduces a key finding

    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
    m
    -1.76
     https
    -1.57
    in
    -1.57
    n
    -1.48
     http
    -1.45
     www
    -1.42
     در
    -1.41
    v
    -1.41
    ina
    -1.41
     «
    -1.39
    POSITIVE LOGITS
     like
    1.82
     unlike
    1.72
     Sakit
    1.66
    Kde
    1.60
     verranno
    1.60
     how
    1.56
     辣
    1.52
     only
    1.52
     while
    1.50
     by
    1.48
    Activations Density 0.076%

    No Known Activations