© 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. 246146
    Prev
    Next
    INDEX
    Explanations

    Bras

    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
     온도
    0.61
     dechlorination
    0.53
     Oahu
    0.52
     Pleistocene
    0.52
     ちゃっ
    0.52
    데
    0.50
    وک
    0.49
     tantalum
    0.49
     colloidal
    0.49
    🄴
    0.49
    POSITIVE LOGITS
    Bras
    0.50
    BRAS
    0.48
    siz
    0.48
    SH
    0.46
    -
    0.45
    Brad
    0.44
    Av
    0.42
    NIC
    0.42
    Raj
    0.42
     उद्यम
    0.42
    Activations Density 0.000%

    No Known Activations