© 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. 10-GEMMASCOPE-RES-131K
    7. 84474
    Prev
    Next
    INDEX
    Explanations

    connect or establish

    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
     atentos
    -1.95
    蛲
    -1.83
     listos
    -1.77
    también
    -1.73
    menü
    -1.63
    躂
    -1.61
     cuillère
    -1.60
     joyería
    -1.58
     również
    -1.58
    镡
    -1.56
    POSITIVE LOGITS
     will
    2.73
     three
    1.89
     two
    1.74
     they
    1.70
     it
    1.70
     made
    1.56
     can
    1.52
    re
    1.47
     four
    1.45
     each
    1.40
    Activations Density 0.015%

    No Known Activations