© 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. 102979
    Prev
    Next
    INDEX
    Explanations

    copies of

    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
    \
    -3.75
    </b>
    -2.97
    =
    -2.88
    (
    -2.58
     \
    -2.52
    K
    -2.52
    ra
    -2.50
     &
    -2.48
    _
    -2.47
     -
    -2.42
    POSITIVE LOGITS
    CurtirCurtir
    3.66
    焄
    2.95
    ਲ਼
    2.91
    瑒
    2.73
    ㈪
    2.66
    伋
    2.61
    읖
    2.59
    珰
    2.58
    enfone
    2.58
    umbnail
    2.58
    Activations Density 0.013%

    No Known Activations