© 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. 101304
    Prev
    Next
    INDEX
    Explanations

    weight units (lb, kg)

    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
    नलोड
    -3.16
    ↵
    -2.97
    </h3>
    -2.95
    荭
    -2.77
    ”
    -2.69
    〤
    -2.44
    心头
    -2.36
    jgl
    -2.34
     چهار
    -2.30
     einf
    -2.25
    POSITIVE LOGITS
    ຼ
    2.66
    ?"
    2.63
    莇
    2.52
     rusa
    2.44
    是有
    2.39
    𓐍
    2.36
    咔嚓
    2.30
    輅
    2.28
    \
    2.23
    讴
    2.22
    Activations Density 0.001%

    No Known Activations