© 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. 128878
    Prev
    Next
    INDEX
    Explanations

    commercialization

    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
     stren
    -2.03
    を選ぶ
    -1.92
    の存在
    -1.91
    鈥
    -1.91
    ピアス
    -1.87
     magnific
    -1.83
     regroupe
    -1.81
     sooo
    -1.81
    sistent
    -1.79
    ᐠ
    -1.77
    POSITIVE LOGITS
     new
    1.87
     wojny
    1.73
    龊
    1.71
     enormous
    1.70
    k
    1.65
     füllen
    1.63
    鋮
    1.62
    i
    1.61
    just
    1.59
     frantic
    1.59
    Activations Density 0.015%

    No Known Activations