© 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. 180455
    Prev
    Next
    INDEX
    Explanations

    concrete mix design inspiration

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

    contrasting with

    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
    Not in Any Lists

    No Comments

    Negative Logits
     موسی
    0.56
    侔
    0.52
    STITUTION
    0.48
     puisque
    0.48
     जहाज़
    0.48
     chargé
    0.48
     meneg
    0.47
     ہوئی
    0.47
     gelişmeler
    0.47
    赁
    0.46
    POSITIVE LOGITS
     \%
    0.55
     and
    0.53
     curved
    0.53
    þ
    0.53
    8
    0.51
    ++
    0.50
     rotated
    0.50
    span
    0.50
    階
    0.50
    rotated
    0.49
    Activations Density 0.000%

    No Known Activations