© 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. 60020
    Prev
    Next
    INDEX
    Explanations

    first name luis

    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
    ↵
    -3.59
    !
    -2.91
    ?
    -2.67
    a
    -2.58
     —
    -2.56
    .
    -2.47
     This
    -2.44
    “
    -2.44
    ."
    -2.31
    可不是
    -2.28
    POSITIVE LOGITS
    鉨
    2.55
     achten
    2.55
    ⬮
    2.52
    那个人
    2.50
    汌
    2.42
    也會
    2.42
     gier
    2.36
    tafogo
    2.30
     hjelp
    2.30
    面对
    2.30
    Activations Density 0.004%

    No Known Activations