© 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. 20496
    Prev
    Next
    INDEX
    Explanations

    actions associated with steps or obligations

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

    communication, next, UP, MPC, LAN

    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
    ле
    0.53
    пта
    0.48
    сима
    0.47
     แทน
    0.47
    樘
    0.47
    ంత్రి
    0.46
    enal
    0.46
    льного
    0.45
    aved
    0.45
     Марина
    0.44
    POSITIVE LOGITS
     circuitry
    0.54
     transients
    0.50
     iteration
    0.49
     jockey
    0.49
     EQUITY
    0.47
     অধিকাংশই
    0.47
     iterations
    0.46
     obligations
    0.46
     violators
    0.46
    「
    0.45
    Activations Density 0.000%

    No Known Activations