© 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. 121292
    Prev
    Next
    INDEX
    Explanations

    validation and confirmation

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

    characters and ideas

    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
    SE
    0.58
     u
    0.58
    W
    0.52
     in
    0.52
    is
    0.51
     is
    0.50
    year
    0.49
    port
    0.49
     i
    0.48
    opp
    0.48
    POSITIVE LOGITS
     устройства
    0.61
     устройств
    0.59
     взаимодействия
    0.56
     тесто
    0.53
     exemples
    0.50
     FIRE
    0.50
     CCSDT
    0.50
     situações
    0.49
     употреб
    0.48
     ძალი
    0.48
    Activations Density 0.000%

    No Known Activations