© 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. 72430
    Prev
    Next
    INDEX
    Explanations

    variable declarations like var, let, const, int

    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
     rése
    -1.99
     kabát
    -1.79
    鳚
    -1.72
     superbe
    -1.66
     évé
    -1.64
     ofici
    -1.63
     transparentes
    -1.62
     incrí
    -1.60
     plafon
    -1.60
     tém
    -1.58
    POSITIVE LOGITS
     it
    2.09
     also
    2.00
    L
    1.84
    f
    1.68
    n
    1.67
    F
    1.62
    D
    1.58
     was
    1.57
    w
    1.57
     can
    1.55
    Activations Density 0.024%

    No Known Activations