© 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. 22-GEMMASCOPE-RES-131K
    7. 27693
    Prev
    Next
    INDEX
    Explanations

    the same

    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_22/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
    趼
    -1.23
     asemenea
    -1.20
    Investi
    -1.12
    囖
    -1.11
    噥
    -1.09
    嚒
    -1.09
    颏
    -1.08
    ￩
    -1.08
     obuv
    -1.07
    Wert
    -1.05
    POSITIVE LOGITS
     that
    1.46
     of
    1.27
     those
    1.15
     there
    1.14
     when
    1.12
     or
    1.09
    /
    1.08
     whose
    1.04
    when
    0.97
     which
    0.97
    Activations Density 0.039%

    No Known Activations