© 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. 128218
    Prev
    Next
    INDEX
    Explanations

    single vs distributed items

    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
    イヤル
    -0.88
    colorbar
    -0.82
    гка
    -0.81
    lott
    -0.79
     Forte
    -0.77
     Spar
    -0.76
    みや
    -0.76
    大致
    -0.75
    レッジ
    -0.74
     sper
    -0.72
    POSITIVE LOGITS
     single
    1.02
    ោ
    0.81
     SINGLE
    0.80
    single
    0.78
    𝙋
    0.77
    findOne
    0.76
    impri
    0.76
    Single
    0.75
    單
    0.75
    getOne
    0.75
    Activations Density 0.104%

    No Known Activations