© 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. 22-GEMMASCOPE-RES-131K
    7. 64898
    Prev
    Next
    INDEX
    Explanations

    flare angle

    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
     następujące
    -1.05
    ⓣ
    -1.03
     decrease
    -1.01
    有不少
    -0.98
     シルエット
    -0.98
     shorter
    -0.97
    dó
    -0.97
    有好
    -0.94
     Abonnez
    -0.94
     connects
    -0.94
    POSITIVE LOGITS
    ‼
    1.05
    ⬮
    1.01
    ﾃ
    1.01
    ～！
    1.00
    সূত্র
    1.00
    ţa
    0.99
     første
    0.98
    iania
    0.97
    atiz
    0.95
    ")}
    0.95
    Activations Density 0.081%

    No Known Activations