© 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. 13337
    Prev
    Next
    INDEX
    Explanations

    automotive parts and components

    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
    gucig
    -1.70
    鹮
    -1.70
    ються
    -1.59
     والتي
    -1.55
     deterior
    -1.48
     majú
    -1.47
     แต่
    -1.45
    🈺
    -1.45
     assurent
    -1.45
    originally
    -1.44
    POSITIVE LOGITS
    ルム
    1.47
    七十
    1.44
    九月
    1.41
     Everything
    1.39
    刹那
    1.38
    ଼
    1.38
    愬
    1.37
    旋律
    1.36
    ）-
    1.35
    AutoScaleMode
    1.33
    Activations Density 0.010%

    No Known Activations