© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181010
    Prev
    Next
    INDEX
    Explanations

    listed below

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

    respect, awe, SLAs

    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
     '';
    0.50
     світу
    0.49
     装
    0.49
     Сьогодні
    0.48
     Hye
    0.48
    ಗೊಳ್ಳ
    0.47
     здоров
    0.47
     ఇండియా
    0.46
     Бор
    0.46
    ;,
    0.46
    POSITIVE LOGITS
     is
    0.57
    slut
    0.52
    ย
    0.49
    促
    0.48
    sn
    0.47
    res
    0.47
    screens
    0.47
    het
    0.46
     prakt
    0.46
    erca
    0.46
    Activations Density 0.000%

    No Known Activations