© 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. 249993
    Prev
    Next
    INDEX
    Explanations

    phrases starting with a, for, through, dear, acquired, providers

    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
     bend
    0.46
     presiding
    0.46
     chiefly
    0.44
     principally
    0.44
     anesthet
    0.44
    emic
    0.43
     being
    0.43
     مربع
    0.43
     graces
    0.42
     ৬
    0.42
    POSITIVE LOGITS
    栆
    0.47
    udet
    0.47
    軺
    0.46
    ums
    0.44
     ediyoruz
    0.43
    MD
    0.43
    Pokud
    0.43
    HY
    0.42
    Muy
    0.42
    jum
    0.42
    Activations Density 0.000%

    No Known Activations