© 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. 123795
    Prev
    Next
    INDEX
    Explanations

    sports leagues, Garmin, Google

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

    math and code generation

    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
     Bahamas
    0.49
     and
    0.46
     -
    0.44
     sporadic
    0.43
     Arabic
    0.42
     factual
    0.41
     seaw
    0.41
     excavations
    0.41
    loxy
    0.40
     concord
    0.40
    POSITIVE LOGITS
    Saturation
    0.47
     นาย
    0.47
    Upper
    0.46
    Aim
    0.46
    Seeking
    0.46
     八
    0.45
    ท
    0.45
    Colorful
    0.44
     plafond
    0.44
    Eight
    0.44
    Activations Density 0.001%

    No Known Activations