© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2432
    Prev
    Next
    INDEX
    Explanations

    reversed text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    이
    1.02
    정
    1.02
     무
    1.01
    만
    1.00
    을
    0.98
     모
    0.96
    기
    0.96
    도
    0.96
     몇
    0.95
     일본
    0.95
    POSITIVE LOGITS
     එම
    0.80
    ؛
    0.77
    ﻥ
    0.76
    ographics
    0.71
     ؛
    0.71
     څرنګ
    0.71
    صاف
    0.71
    تيجة
    0.70
    ائص
    0.70
     وګټ
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.