© 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. 73516
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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
    .
    -2.80
    </b>
    -2.47
     síntesis
    -2.39
    驮
    -2.39
    𓍊
    -2.20
     but
    -2.16
     elabor
    -2.14
    交渉
    -2.13
    茏
    -2.09
    Ārējās
    -2.06
    POSITIVE LOGITS
    h
    3.03
    </h3>
    2.97
    “
    2.88
    蕻
    2.80
    '
    2.58
     :/
    2.50
     Perfon
    2.48
    of
    2.45
    ル
    2.42
    ?"
    2.34
    Activations Density 0.034%

    No Known Activations