© 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. 151202
    Prev
    Next
    INDEX
    Explanations

    electrically grounded

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

    select answer or based on

    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
    wirkung
    0.49
    佑
    0.48
    adri
    0.46
    UER
    0.45
    humans
    0.44
     Ps
    0.42
    proble
    0.42
    ਾਈ
    0.41
    诩
    0.41
     suspected
    0.41
    POSITIVE LOGITS
     of
    0.69
     into
    0.57
     τῶν
    0.56
     Of
    0.55
     của
    0.52
     ഓഫ്
    0.48
     dve
    0.48
     nField
    0.48
     locomotive
    0.47
     должна
    0.46
    Activations Density 0.000%

    No Known Activations