© 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. 238604
    Prev
    Next
    INDEX
    Explanations

    official roles and actions

    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
     sideWeight
    0.46
     Sack
    0.42
    rava
    0.42
    ton
    0.42
    rika
    0.41
    ();
    0.41
     Jon
    0.40
    hetamine
    0.39
    gel
    0.39
     throwIfNotFound
    0.39
    POSITIVE LOGITS
    academic
    0.52
    Academic
    0.52
     aceste
    0.52
     exposures
    0.51
     internships
    0.49
    ֶ
    0.48
    каде
    0.48
     Kyi
    0.48
     queste
    0.48
     precincts
    0.47
    Activations Density 0.005%

    No Known Activations