© 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. 114090
    Prev
    Next
    INDEX
    Explanations

    Get Around

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

    asking "what" does it mean

    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
    위를
    0.54
    enture
    0.46
    小米
    0.45
     uczest
    0.44
    ام
    0.44
    意见
    0.43
    빌
    0.42
    කාර
    0.42
     únicamente
    0.42
     milliliters
    0.42
    POSITIVE LOGITS
    than
    0.52
    maan
    0.49
    ósticos
    0.49
    θ
    0.48
    cted
    0.47
    etaan
    0.46
     wheelbase
    0.44
    jadi
    0.44
    wrapping
    0.44
    ean
    0.43
    Activations Density 0.001%

    No Known Activations