© 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. 105159
    Prev
    Next
    INDEX
    Explanations

    month period reporting

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

    dates and facts

    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
     אם
    0.50
    ב
    0.49
    ﻀ
    0.46
     אני
    0.46
    我现在
    0.46
     উল্লেখ
    0.43
    Tôi
    0.43
    Code
    0.43
    Collegamenti
    0.43
     especial
    0.43
    POSITIVE LOGITS
     ry
    0.54
    <0x93>
    0.53
     jie
    0.50
     रुपया
    0.50
     kartu
    0.50
    arlo
    0.48
     dosa
    0.48
     kopi
    0.47
     vej
    0.47
     yuan
    0.46
    Activations Density 0.000%

    No Known Activations