© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141261
    Prev
    Next
    INDEX
    Explanations

    earth situationsworshipRelease Form

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

    card ranks and suits

    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
    Negative Logits
     legacy
    0.49
     непри
    0.45
     писа
    0.44
     معاون
    0.44
     نام
    0.44
     apologize
    0.44
     innovating
    0.43
     apologise
    0.42
    및
    0.42
     ancient
    0.42
    POSITIVE LOGITS
     Hampshire
    0.59
    GIF
    0.52
    ak
    0.52
    Peek
    0.51
    ENER
    0.50
     Staffordshire
    0.50
    IFT
    0.49
    heus
    0.49
    sgn
    0.49
    сия
    0.48
    Activations Density 0.006%

    No Known Activations