© 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. 139255
    Prev
    Next
    INDEX
    Explanations

    sharing or possibilities information

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

    Returns: tuple, sequence `and` `update`

    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
    釹
    0.49
    ľad
    0.47
    謾
    0.47
     thermost
    0.46
    ệng
    0.46
    發生
    0.45
    墮
    0.45
     Cang
    0.44
     sadistic
    0.44
     coarse
    0.44
    POSITIVE LOGITS
     partager
    0.56
    د
    0.55
     événements
    0.54
     indiquer
    0.53
     ouvrir
    0.53
     possibilidades
    0.50
    ${
    0.50
     posibilidades
    0.50
    $).
    0.49
     comparte
    0.49
    Activations Density 0.000%

    No Known Activations