© 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. 108147
    Prev
    Next
    INDEX
    Explanations

    legal phrases and copyright notices

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

    attempting to do certain actions

    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
     которого
    0.49
     Игорь
    0.47
     Чар
    0.47
    然而
    0.46
     Krzy
    0.46
    那时
    0.45
     esemplare
    0.45
     Unterschied
    0.45
    也不会
    0.44
    顗
    0.44
    POSITIVE LOGITS
    ien
    0.54
    ij
    0.52
    out
    0.51
    ac
    0.47
     patients
    0.46
    inds
    0.46
     निकायों
    0.46
    iv
    0.45
    ingles
    0.44
    headings
    0.43
    Activations Density 0.001%

    No Known Activations