© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233968
    Prev
    Next
    INDEX
    Explanations

    security measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    海水
    0.51
    ের
    0.50
    Tá
    0.50
    આ
    0.50
     квадра
    0.49
    ଦ
    0.49
    На
    0.49
    Спо
    0.49
    مہ
    0.49
    Ди
    0.48
    POSITIVE LOGITS
    p
    0.56
     p
    0.54
    gerufen
    0.53
     ABC
    0.52
     Saber
    0.49
    oping
    0.49
     Leibniz
    0.48
     Beruf
    0.48
     saber
    0.47
     Ming
    0.47
    Activations Density 0.001%

    No Known Activations