© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5804
    Prev
    Next
    INDEX
    Explanations

    title of

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

    defining types and styles

    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
    fabs
    0.61
    conse
    0.59
    vf
    0.58
    v
    0.58
    au
    0.57
    il
    0.57
    math
    0.57
    jie
    0.56
    z
    0.55
    ؛
    0.55
    POSITIVE LOGITS
     terrorism
    0.56
     lLoginID
    0.55
     nessuna
    0.52
     NAND
    0.51
    囔
    0.51
    櫥
    0.50
     operazioni
    0.50
     stessi
    0.48
    चालित
    0.48
     internazionali
    0.48
    Activations Density 0.000%

    No Known Activations