© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34794
    Prev
    Next
    INDEX
    Explanations

    loop structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دام
    1.40
    ب
    1.39
    ['
    1.23
    דה
    1.23
    ميم
    1.23
    dür
    1.18
    で
    1.17
    dependent
    1.16
    ই
    1.15
    부터
    1.14
    POSITIVE LOGITS
    א
    1.63
     sırada
    1.47
    みました
    1.40
     bentuk
    1.35
    ни
    1.27
     acontecimientos
    1.26
     starken
    1.25
    Архівовано
    1.23
     Forgotten
    1.23
     sogenannten
    1.21
    Activations Density 0.022%

    No Known Activations