© 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. 34-GEMMASCOPE-RES-131K
    4. 92384
    Prev
    Next
    INDEX
    Explanations

    http URL links

    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_34/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
     long
    -0.83
     dropped
    -0.77
    quy
    -0.71
     caso
    -0.70
     choose
    -0.70
    틀
    -0.67
    喘
    -0.66
     cho
    -0.65
     selecting
    -0.65
    rie
    -0.65
    POSITIVE LOGITS
     GILL
    0.81
    centage
    0.78
    ()};
    0.73
    סים
    0.72
     '../
    0.71
     Tatum
    0.71
     Raptors
    0.70
    (',');
    0.69
    Feeding
    0.69
    worpen
    0.69
    Activations Density 0.056%

    No Known Activations