© 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. 34-GEMMASCOPE-RES-131K
    7. 78355
    Prev
    Next
    INDEX
    Explanations

    names, places, dates, titles

    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_34/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
     arşivlendi
    -1.73
    (!__
    -1.66
     (!__
    -1.52
    」。
    -1.28
    [].
    -1.26
     }}$,
    -1.23
     ?,
    -1.22
     ?.
    -1.22
    }$.
    -1.20
    ?).
    -1.20
    POSITIVE LOGITS
     (
    4.06
    」（
    2.67
    』（
    2.64
    .(
    2.44
    )(
    2.14
    ”（
    2.13
    》（
    2.03
    」(
    2.00
    ）（
    1.95
    ”(
    1.92
    Activations Density 0.104%

    No Known Activations