© 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. 22-GEMMASCOPE-RES-131K
    7. 64813
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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_22/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
     kabát
    -1.77
     kré
    -1.57
     histó
    -1.55
     rése
    -1.52
    𓆏
    -1.46
    ଃ
    -1.42
     phénom
    -1.42
     filmu
    -1.41
     čier
    -1.40
     célè
    -1.39
    POSITIVE LOGITS
     at
    1.68
     if
    1.67
     it
    1.64
     changed
    1.61
     knew
    1.59
     from
    1.58
     not
    1.57
     until
    1.56
     should
    1.52
     new
    1.51
    Activations Density 0.008%

    No Known Activations