© 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. 206990
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

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

    discussing harm or illegal activities

    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
     importantes
    0.47
    برا
    0.46
     vyber
    0.46
    關於
    0.45
    ക
    0.44
    頊
    0.43
    下一
    0.42
    প্রথম
    0.42
    噦
    0.42
    Xiaomi
    0.42
    POSITIVE LOGITS
     ballot
    0.57
    nego
    0.54
     კან
    0.47
     surplus
    0.47
     スウェット
    0.47
    ohnt
    0.47
     Recht
    0.47
     spitting
    0.47
    ei
    0.46
    䐂
    0.46
    Activations Density 0.001%

    No Known Activations