© 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. 73425
    Prev
    Next
    INDEX
    Explanations

    reading information and records

    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
    ,
    -1.08
    —
    -1.04
    large
    -1.00
     K
    -0.98
    Others
    -0.97
     lovely
    -0.96
    ...
    -0.95
     —
    -0.93
    lov
    -0.93
    z
    -0.92
    POSITIVE LOGITS
     and
    2.03
     tertulis
    1.05
    apnews
    1.03
    éta
    1.02
    ochemical
    1.00
     및
    0.98
     consommate
    0.98
    หรือ
    0.94
    accompanied
    0.94
     financieros
    0.94
    Activations Density 0.112%

    No Known Activations