© 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. 245301
    Prev
    Next
    INDEX
    Explanations

    C/C++ macro definitions

    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
    s
    0.73
    1
    0.59
    d
    0.57
    table
    0.55
    m
    0.55
    *:
    0.55
    design
    0.53
    стан
    0.52
    t
    0.52
     aren
    0.48
    POSITIVE LOGITS
     tentunya
    0.61
     ತ
    0.60
    ವೇಂದ್ರ
    0.59
     pembayaran
    0.58
     pidió
    0.57
     retweet
    0.54
     cepat
    0.53
    ವರ
    0.53
     रक्कम
    0.53
     沒有
    0.52
    Activations Density 0.000%

    No Known Activations