© 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. 64820
    Prev
    Next
    INDEX
    Explanations

    specific concepts or entities

    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
    .
    -1.43
     also
    -1.38
     instead
    -1.19
     nobre
    -1.13
    v
    -1.13
    —
    -1.12
    '
    -1.02
     decidedly
    -1.01
     além
    -1.01
     contributing
    -1.01
    POSITIVE LOGITS
    pisode
    1.13
     direkte
    1.07
    🏃
    1.06
    TOE
    1.06
    鴉
    1.04
     kolye
    1.04
     parlé
    1.02
    曄
    1.02
     @"";
    1.02
     köt
    1.01
    Activations Density 0.202%

    No Known Activations