© 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. 139979
    Prev
    Next
    INDEX
    Explanations

    know or understand requirements

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

    identifying specific nouns

    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
    惨
    0.48
    Years
    0.47
    Kết
    0.47
    惶
    0.46
    Hola
    0.46
    罢
    0.46
    об
    0.44
    の違い
    0.44
     quantifiable
    0.44
    缪
    0.44
    POSITIVE LOGITS
     to
    0.55
    iados
    0.49
     Utilizing
    0.48
    ings
    0.46
    GY
    0.46
     utrzym
    0.45
    kungan
    0.45
    dnn
    0.45
    geg
    0.44
     Lin
    0.44
    Activations Density 0.000%

    No Known Activations