© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130236
    Prev
    Next
    INDEX
    Explanations

    article titles and labels

    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
     pleas
    -2.52
    or
    -2.36
     pinnacle
    -2.30
    (\
    -2.28
     we
    -2.28
    花板
    -2.22
     kterou
    -2.20
     i
    -2.19
     alters
    -2.19
    achting
    -2.17
    POSITIVE LOGITS
    唻
    3.17
    薆
    2.69
    婓
    2.33
    ኧ
    2.33
    更多的
    2.27
     unangemessene
    2.23
     pakan
    2.22
     menn
    2.20
     rústica
    2.20
    有趣的
    2.20
    Activations Density 0.000%

    No Known Activations