© 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. 41065
    Prev
    Next
    INDEX
    Explanations

    we have

    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
     können
    -1.81
     be
    -1.66
    เกง
    -1.63
    两个
    -1.55
    爽
    -1.54
    
    -1.54
    さん
    -1.53
    Galeria
    -1.52
    تیجه
    -1.48
    sendStatus
    -1.48
    POSITIVE LOGITS
     that
    2.20
     loadImage
    1.59
    ⸰
    1.52
     to
    1.48
     sichere
    1.48
    ㆆ
    1.45
    mpagne
    1.43
     either
    1.42
     égard
    1.41
    唎
    1.41
    Activations Density 0.055%

    No Known Activations