© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13271
    Prev
    Next
    INDEX
    Explanations

    at the time

    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_10/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
     only
    -1.96
    每一个
    -1.57
     also
    -1.57
     even
    -1.52
     celebrado
    -1.52
     Durchschnitt
    -1.52
    _{\
    -1.50
     Accesorios
    -1.49
    wendungs
    -1.48
    なども
    -1.47
    POSITIVE LOGITS
     they
    1.88
    ↵
    1.81
    
    1.73
    謌
    1.65
    that
    1.63
    as
    1.62
     rapida
    1.59
    v
    1.56
    u
    1.52
    ina
    1.51
    Activations Density 0.015%

    No Known Activations