© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80233
    Prev
    Next
    INDEX
    Explanations

    absorb energy

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ять
    0.52
    راهيم
    0.48
    ي
    0.48
    و
    0.47
    燬
    0.47
     يَ
    0.47
    йон
    0.45
    㑼
    0.45
    嚨
    0.45
     gerçek
    0.44
    POSITIVE LOGITS
     with
    0.53
     as
    0.53
     when
    0.49
     at
    0.48
     Courses
    0.47
    typed
    0.47
     Sets
    0.47
    known
    0.46
     into
    0.45
     Bás
    0.44
    Activations Density 0.003%

    No Known Activations