© 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. 111025
    Prev
    Next
    INDEX
    Explanations

    preventing or stopping negative actions

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

    database connection

    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
    sk
    0.52
    dalam
    0.51
    அது
    0.49
    children
    0.49
    lady
    0.48
    lg
    0.48
    otland
    0.48
    น
    0.47
    log
    0.47
    по
    0.46
    POSITIVE LOGITS
     restraining
    0.48
     ਦਿੱ
    0.43
    獲得
    0.43
    )}}{
    0.43
     Withers
    0.42
     massac
    0.42
     breech
    0.42
     wounding
    0.41
     Wolver
    0.41
     depositions
    0.41
    Activations Density 0.000%

    No Known Activations