Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8247
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY

    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
     progesterone
    -0.82
    hecimento
    -0.75
     Delphi
    -0.75
    gesterone
    -0.73
    getLeft
    -0.73
     双
    -0.72
     ведь
    -0.70
    DoubleClick
    -0.69
    randi
    -0.69
    msb
    -0.68
    POSITIVE LOGITS
     weathering
    0.68
    gé
    0.67
     Петер
    0.66
    hawa
    0.66
     Buckley
    0.66
    phoria
    0.66
     Key
    0.65
     Fauna
    0.63
    了一种
    0.63
    学び
    0.63
    Activations Density 0.059%

    No Known Activations