© 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. 85353
    Prev
    Next
    INDEX
    Explanations

    state/event related content

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

    individuals, lifespan, Station, status

    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
    ไว
    0.44
    ة
    0.44
     accompagnée
    0.43
    雙
    0.43
    )
    0.43
    ת
    0.43
    你需要
    0.42
    .
    0.42
    _
    0.41
     debuts
    0.41
    POSITIVE LOGITS
     knowledge
    0.44
     hầu
    0.43
    ற்ச
    0.43
    berat
    0.42
     -*-
    0.42
     मनो
    0.42
     Radiation
    0.42
    engineer
    0.42
     profound
    0.41
    psych
    0.41
    Activations Density 0.001%

    No Known Activations