© 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. 73802
    Prev
    Next
    INDEX
    Explanations

    #define statements

    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
     –
    -1.66
     to
    -1.65
     of
    -1.63
     from
    -1.60
     (
    -1.55
     out
    -1.52
     that
    -1.50
     including
    -1.49
     it
    -1.49
    —
    -1.47
    POSITIVE LOGITS
    该如何
    1.80
     descuentos
    1.73
    ՙ
    1.70
     ajuta
    1.65
     ARNOLD
    1.64
     Consejos
    1.63
     regresa
    1.55
     Pentru
    1.55
     سار
    1.55
    承担
    1.54
    Activations Density 0.024%

    No Known Activations