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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78082
    Prev
    Next
    INDEX
    Explanations

    book titles and author names

    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
     फ़
    -0.77
    vaný
    -0.75
    вича
    -0.73
    IMPORTED
    -0.70
    ством
    -0.70
     pe
    -0.69
    すす
    -0.69
    Ĩ
    -0.68
    がお
    -0.68
     Clara
    -0.68
    POSITIVE LOGITS
     EH
    0.96
    뉘
    0.91
     ERC
    0.89
     EI
    0.85
     EK
    0.84
     EO
    0.83
    のエ
    0.83
    lious
    0.80
    бва
    0.79
     Klassi
    0.77
    Activations Density 1.473%

    No Known Activations