© 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. 58922
    Prev
    Next
    INDEX
    Explanations

    skating rink

    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
    ية
    -4.09
    
    -3.23
    вання
    -3.00
    ized
    -2.61
    ся
    -2.59
    jší
    -2.58
    衪
    -2.52
    ression
    -2.52
    在自己
    -2.50
     Scritto
    -2.48
    POSITIVE LOGITS
    a
    3.81
     was
    3.66
    i
    3.02
     {
    2.88
    wiście
    2.72
    胧
    2.69
    抡
    2.34
     (
    2.27
     in
    2.17
    s
    2.16
    Activations Density 0.032%

    No Known Activations