© 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. 144592
    Prev
    Next
    INDEX
    Explanations

    specialized items and descriptions

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

    physical gratification, personal connection, class

    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
    నో
    0.46
    pi
    0.46
    N
    0.46
    ky
    0.45
    n
    0.44
     Nato
    0.44
     रमा
    0.43
    ecc
    0.43
    -
    0.43
    ۴
    0.42
    POSITIVE LOGITS
    әр
    0.51
    同様
    0.50
     waterslide
    0.49
     armband
    0.46
     diagram
    0.45
     subwoofer
    0.45
     mirroring
    0.45
     antérieure
    0.44
     tutur
    0.44
     bookcase
    0.43
    Activations Density 0.000%

    No Known Activations