© 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. 43930
    Prev
    Next
    INDEX
    Explanations

    Code documentation headers

    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
     kochen
    -1.41
     komplex
    -1.41
     comprando
    -1.36
    USTER
    -1.34
     nyeri
    -1.34
     Szen
    -1.33
    dians
    -1.33
     komplet
    -1.30
    aktionen
    -1.30
    riy
    -1.29
    POSITIVE LOGITS
     to
    2.03
     for
    1.77
     just
    1.70
     with
    1.63
     profoundly
    1.55
     allows
    1.52
    Both
    1.50
    Perhaps
    1.50
     really
    1.48
    Each
    1.48
    Activations Density 0.024%

    No Known Activations