© 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. 75798
    Prev
    Next
    INDEX
    Explanations

    any questions

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

    theory of mind and methods

    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
     خطوات
    0.49
    島の
    0.46
     کھانے
    0.46
    ्या
    0.46
    uların
    0.46
     দুপুর
    0.46
     elaborar
    0.45
     educativas
    0.44
    詿
    0.44
    اویز
    0.44
    POSITIVE LOGITS
    STR
    0.63
     يلا
    0.48
     STR
    0.46
     to
    0.44
     Oder
    0.43
     Spal
    0.43
     Sergio
    0.43
    wtf
    0.43
    čení
    0.42
     McGuire
    0.42
    Activations Density 0.000%

    No Known Activations