© 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. 64031
    Prev
    Next
    INDEX
    Explanations

    types of diabetes

    np_acts-logits-general · gemini-2.5-flash-lite

    French, language, code, iteration

    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
     AFTER
    0.49
     RAIL
    0.47
     strengthened
    0.47
     dụng
    0.46
    羟
    0.45
    ർ
    0.44
    َم
    0.44
    的时
    0.44
    证据
    0.43
     ROOM
    0.43
    POSITIVE LOGITS
    lining
    0.43
     encirc
    0.43
     बचे
    0.42
     स्थ
    0.41
    ructive
    0.40
     envious
    0.40
    rupt
    0.39
     pessimism
    0.39
     leth
    0.39
     fixa
    0.39
    Activations Density 0.000%

    No Known Activations