© 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. 73699
    Prev
    Next
    INDEX
    Explanations

    excellent [noun] of/to/for

    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
     depending
    -1.92
    骘
    -1.83
    皝
    -1.72
     incidents
    -1.67
    volent
    -1.59
    ⃨
    -1.59
    bilities
    -1.58
    当成
    -1.56
     unable
    -1.55
    bảng
    -1.55
    POSITIVE LOGITS
    <strong>
    1.91
    Just
    1.68
    There
    1.68
    Would
    1.66
    If
    1.62
    Â
    1.56
    而
    1.55
    While
    1.54
    Very
    1.54
     .
    1.54
    Activations Density 0.019%

    No Known Activations