© 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. 127430
    Prev
    Next
    INDEX
    Explanations

    struggling to or with

    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
    튿
    -3.11
    訁
    -2.89
     kosme
    -2.69
    푙
    -2.56
    羮
    -2.56
    屨
    -2.56
    壼
    -2.55
    Ꮉ
    -2.52
    氿
    -2.52
    廰
    -2.50
    POSITIVE LOGITS
    ’
    3.42
    ",
    2.78
     —
    2.73
    ”,
    2.73
    ..
    2.70
    ".
    2.66
     $
    2.55
    ;
    2.50
    .
    2.44
    ."
    2.38
    Activations Density 0.004%

    No Known Activations