© 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. 152120
    Prev
    Next
    INDEX
    Explanations

    finding or launching something

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

    information and instructions

    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
    дут
    0.48
    かし
    0.47
    凯
    0.45
    d
    0.45
    우리
    0.44
    abaya
    0.43
     फ्रा
    0.42
    了
    0.42
    t
    0.42
     Бер
    0.42
    POSITIVE LOGITS
     anthropogenic
    0.48
     galaxies
    0.48
     regenerative
    0.47
     subsidence
    0.46
     isotropy
    0.46
     malnutrition
    0.46
     ಶತ
    0.45
     ಅಧಿಕ
    0.45
     leptonic
    0.45
     for
    0.45
    Activations Density 0.001%

    No Known Activations