© 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. 86867
    Prev
    Next
    INDEX
    Explanations

    producing guidance, brands of, furniture sets

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

    variations, concentration, peak, solutions

    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
    c
    0.70
    t
    0.63
    r
    0.59
     Rosie
    0.53
    o
    0.52
    轉
    0.50
    ka
    0.49
    i
    0.49
     Public
    0.48
    CO
    0.46
    POSITIVE LOGITS
     número
    0.59
     veía
    0.56
     ヘッド
    0.53
    㑼
    0.53
     curto
    0.52
    RationalValue
    0.52
    CriteriaUtils
    0.52
     artículos
    0.52
     calmness
    0.52
    MatContext
    0.52
    Activations Density 0.000%

    No Known Activations