© 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. 185170
    Prev
    Next
    INDEX
    Explanations

    teams and projects

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

    counting parameters, total, per hour, female

    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
    Yet
    0.46
    gli
    0.46
    டு
    0.46
    ør
    0.45
    阮
    0.43
    梦
    0.43
    湁
    0.43
    sub
    0.42
    6
    0.42
    stup
    0.42
    POSITIVE LOGITS
     candlestick
    0.49
     derivados
    0.49
     buscando
    0.47
     FEM
    0.47
     halides
    0.47
     titan
    0.47
     poised
    0.46
    तीच्या
    0.46
     Titans
    0.45
     titans
    0.45
    Activations Density 0.001%

    No Known Activations