© 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. 75576
    Prev
    Next
    INDEX
    Explanations

    sales figures and percentages

    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
     Fors
    -0.88
     capsule
    -0.85
    ELL
    -0.79
    Courier
    -0.79
    /******/
    -0.77
     Clarkson
    -0.77
    <?=$
    -0.77
    CACHE
    -0.72
    %@",
    -0.72
     Dj
    -0.71
    POSITIVE LOGITS
     shopper
    0.97
     shoppers
    0.93
     measured
    0.84
     settimana
    0.82
     velocities
    0.79
     grocery
    0.77
    Grocery
    0.77
     것입니다
    0.75
    gehen
    0.75
     retailer
    0.75
    Activations Density 0.020%

    No Known Activations