© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34523
    Prev
    Next
    INDEX
    Explanations

    two legs, +/-, Northern, Arena

    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
     still
    -0.88
     regress
    -0.85
     compromiso
    -0.81
     haga
    -0.80
     from
    -0.80
     has
    -0.80
     as
    -0.79
    1
    -0.79
     with
    -0.77
     défaite
    -0.77
    POSITIVE LOGITS
     bezw
    1.02
     messen
    1.02
     filmen
    0.99
    ENCIAS
    0.98
     sehe
    0.96
    setState
    0.94
     externes
    0.93
    ଵ
    0.93
     ſtre
    0.93
     interak
    0.91
    Activations Density 0.089%

    No Known Activations