© 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. 187144
    Prev
    Next
    INDEX
    Explanations

    directly, Russian, Korean

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

    XOR, data, rules, bearer

    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
    -
    0.65
    gun
    0.64
    ine
    0.59
    group
    0.55
    websites
    0.55
    west
    0.53
    nc
    0.53
    k
    0.53
    life
    0.52
    book
    0.52
    POSITIVE LOGITS
    비
    0.54
     直接
    0.54
    Компания
    0.54
    直接
    0.52
    ในปี
    0.50
    सामान्यीकृत
    0.50
    㮍
    0.49
    𝘩
    0.49
     직접
    0.48
    この
    0.48
    Activations Density 0.001%

    No Known Activations