© 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. 35576
    Prev
    Next
    INDEX
    Explanations

    to force, tag another, serve less

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

    relatively friendly

    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
    g
    0.66
    p
    0.61
    r
    0.59
    k
    0.57
    pads
    0.55
    m
    0.55
    y
    0.54
    h
    0.53
     halts
    0.52
    d
    0.50
    POSITIVE LOGITS
     સમય
    0.64
     vegetarian
    0.56
     Vegetarian
    0.54
     `<=`
    0.54
     VALUE
    0.52
     stabilize
    0.52
     nilai
    0.51
     menghadapi
    0.49
     Miao
    0.49
     চীনা
    0.49
    Activations Density 0.000%

    No Known Activations