© 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. 117882
    Prev
    Next
    INDEX
    Explanations

    under detention or legal proceedings

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

    account or service access

    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
     designado
    0.54
    ében
    0.53
     prosecute
    0.48
    cluding
    0.47
     函数
    0.46
    idot
    0.44
    ével
    0.43
    ifiez
    0.43
     emple
    0.42
    ============
    0.42
    POSITIVE LOGITS
    ቝ
    0.53
    悽
    0.49
    Чер
    0.48
    phenoxy
    0.47
    னிய
    0.46
     gorillas
    0.46
     geologist
    0.46
    רי
    0.46
     pronotum
    0.46
    냅
    0.46
    Activations Density 0.000%

    No Known Activations