© 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. 44832
    Prev
    Next
    INDEX
    Explanations

    XEmacs and unicode quotation marks

    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
    s
    -3.03
    禤
    -2.95
     stattfinden
    -2.95
    </sup>
    -2.94
    腘
    -2.73
     сделал
    -2.64
    橚
    -2.56
    AdvEx
    -2.55
    quelize
    -2.52
    袛
    -2.48
    POSITIVE LOGITS
    (
    2.63
    {
    2.33
    老太太
    2.25
    но
    2.25
     あります
    2.23
     â
    2.16
    er
    2.14
    –
    2.14
    '."
    2.11
    ствия
    2.09
    Activations Density 0.003%

    No Known Activations