© 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. 31482
    Prev
    Next
    INDEX
    Explanations

    questions and queries

    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
    icium
    -0.87
     microbial
    -0.76
     ری
    -0.75
    ∝
    -0.74
    postmedia
    -0.74
    ctuaries
    -0.74
    我还
    -0.73
    ftn
    -0.73
     Đà
    -0.72
    ílica
    -0.72
    POSITIVE LOGITS
     olymp
    0.77
    柬
    0.77
     prostitutes
    0.74
     roboc
    0.74
     ligh
    0.73
    Referencia
    0.72
     BRASIL
    0.69
     AGUA
    0.69
    isnull
    0.68
     moored
    0.66
    Activations Density 0.035%

    No Known Activations