© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70044
    Prev
    Next
    INDEX
    Explanations

    sheet materials

    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
    znym
    -0.75
     twig
    -0.73
     vỏ
    -0.72
    Története
    -0.72
    lave
    -0.71
    一座
    -0.69
    CCI
    -0.69
    وروبا
    -0.69
    xsd
    -0.68
    MONT
    -0.68
    POSITIVE LOGITS
     sheets
    2.75
     sheet
    2.11
     Sheets
    2.09
     lengths
    1.91
     pieces
    1.91
    sheets
    1.82
     Sheet
    1.80
    Sheets
    1.78
     rolls
    1.66
    Sheet
    1.64
    Activations Density 0.088%

    No Known Activations