© 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. 10992
    Prev
    Next
    INDEX
    Explanations

    elsewhere

    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
    躄
    -2.59
    蘄
    -2.45
    </b>
    -2.41
    理会
    -2.41
    慫
    -2.38
    ቷ
    -2.33
    嘥
    -2.33
    archiwizowane
    -2.30
     The
    -2.30
    </i>
    -2.28
    POSITIVE LOGITS
    [
    2.70
    n
    2.70
    "
    2.67
    <strong>
    2.59
    The
    2.56
    8
    2.55
    𞤢
    2.55
    3
    2.55
     maupun
    2.53
    no
    2.42
    Activations Density 0.002%

    No Known Activations