© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101741
    Prev
    Next
    INDEX
    Explanations

    knowingly causing, exposes, patrolling

    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_10/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
     problemi
    -2.69
    瑧
    -2.41
    </i>
    -2.39
     arrivare
    -2.30
     leftover
    -2.30
    idjan
    -2.25
    IANGLES
    -2.20
    苹
    -2.19
    -2.17
    錚
    -2.13
    POSITIVE LOGITS
    殽
    2.98
    ו
    2.81
    婓
    2.52
    t
    2.50
     Their
    2.45
    鞴
    2.36
    <em>
    2.33
    羮
    2.31
     guile
    2.31
     settembre
    2.31
    Activations Density 0.002%

    No Known Activations