© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4669
    Prev
    Next
    INDEX
    Explanations

    heavily reliance on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     На
    0.63
    ну
    0.62
    м
    0.62
    ک
    0.58
     Те
    0.57
    IgnoreCase
    0.57
    すべての
    0.57
    ಧ
    0.56
    ە
    0.56
    ू
    0.55
    POSITIVE LOGITS
    on
    1.02
    er
    0.82
    in
    0.71
    us
    0.67
    i
    0.66
    og
    0.65
    ang
    0.65
    have
    0.63
    )
    0.62
    onk
    0.61
    Activations Density 0.335%

    No Known Activations