© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30106
    Prev
    Next
    INDEX
    Explanations

    dollar sign and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     सास
    0.40
     बांधकाम
    0.39
    }+{\
    0.39
    երը
    0.38
    ampi
    0.36
     लिंग
    0.36
    regierung
    0.35
    }|$
    0.35
    大切な
    0.35
    imha
    0.34
    POSITIVE LOGITS
     ठ
    0.39
    arcz
    0.38
    tener
    0.36
    ර්ග
    0.36
     Thirty
    0.36
     peanut
    0.35
     Tennessee
    0.35
     eosin
    0.35
     Hurry
    0.35
    acağ
    0.34
    Activations Density 0.000%

    No Known Activations