© 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. 87216
    Prev
    Next
    INDEX
    Explanations

    because these, other intellectual, computer make

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

    why the

    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
     выяв
    0.53
     теат
    0.47
     %).
    0.47
     একদম
    0.46
     poetry
    0.46
     fortæ
    0.46
     путем
    0.46
    $-,
    0.46
     театр
    0.45
     самый
    0.45
    POSITIVE LOGITS
    barrier
    0.51
     처리
    0.49
    ID
    0.47
    dire
    0.46
    getter
    0.46
    profissional
    0.46
    stopper
    0.46
    cham
    0.45
    p
    0.45
    pert
    0.44
    Activations Density 0.000%

    No Known Activations