© 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. 38965
    Prev
    Next
    INDEX
    Explanations

    starts of lists or code

    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
     (
    -1.02
    除此之外
    -0.77
     occurrence
    -0.77
     remarque
    -0.77
    kton
    -0.77
    看出
    -0.76
    プログラム
    -0.76
     from
    -0.76
     Klassen
    -0.75
    ्यालय
    -0.73
    POSITIVE LOGITS
     págs
    1.10
     inizi
    0.99
     riten
    0.97
     riuscito
    0.97
     anything
    0.92
     nuovi
    0.92
     giorn
    0.91
    攏
    0.89
     cominci
    0.88
    ὰ
    0.88
    Activations Density 0.000%

    No Known Activations