© 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. 38341
    Prev
    Next
    INDEX
    Explanations

    starts questions or descriptions

    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
     vulgaires
    -1.47
     inappropriés
    -1.41
    謦
    -1.41
    ꉂ
    -1.39
     terlalu
    -1.34
    っとり
    -1.34
     Ál
    -1.30
     inapropiados
    -1.30
    chnung
    -1.29
     définiti
    -1.28
    POSITIVE LOGITS
    D
    1.71
    T
    1.71
    K
    1.54
    e
    1.49
     -
    1.49
    //
    1.45
    M
    1.40
    P
    1.39
    h
    1.37
    E
    1.37
    Activations Density 0.000%

    No Known Activations