© 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. 72939
    Prev
    Next
    INDEX
    Explanations

    code punctuation or function definitions

    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
     our
    -1.06
    ersen
    -0.96
     personalizadas
    -0.86
     Creatures
    -0.85
    ǀ
    -0.82
    indade
    -0.80
     vermelhas
    -0.80
     rozwiąz
    -0.80
    steer
    -0.79
    כן
    -0.78
    POSITIVE LOGITS
    Another
    1.04
    為に
    0.95
     same
    0.92
    ⁣⁣
    0.91
    Détails
    0.90
    Something
    0.86
     descrizione
    0.86
    晌
    0.85
    nodata
    0.85
    いっ
    0.85
    Activations Density 0.002%

    No Known Activations