© 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. 87313
    Prev
    Next
    INDEX
    Explanations

    collection andThe Bantamsthat isusing Google

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

    Data followed by punctuation

    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
     مسائل
    0.55
    DeathRecord
    0.52
     אטאטורק
    0.49
    禪
    0.49
     वय
    0.48
    Lowest
    0.47
     ഡ
    0.47
     جوړونکي
    0.47
     regimens
    0.47
    RELATIVA
    0.46
    POSITIVE LOGITS
     -
    0.52
    ipa
    0.47
     termasuk
    0.46
    ;
    0.45
    main
    0.44
    !
    0.44
    oad
    0.44
     lalu
    0.44
    óp
    0.44
    itung
    0.43
    Activations Density 0.001%

    No Known Activations