© 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. 249418
    Prev
    Next
    INDEX
    Explanations

    dangerous racing, premature babies

    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
    苋
    0.54
    ке
    0.49
     پاورپوینت
    0.47
    assignmentItems
    0.47
     рассказыва
    0.46
    ᆺ
    0.43
     earnestly
    0.43
    еме
    0.43
    ా
    0.43
     lẽ
    0.43
    POSITIVE LOGITS
    un
    0.60
    il
    0.53
    id
    0.52
    check
    0.52
    us
    0.51
    uno
    0.51
    confirm
    0.50
    con
    0.50
    region
    0.49
    niv
    0.49
    Activations Density 0.000%

    No Known Activations