© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    Per

    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
    ាតុ
    0.62
    aggregated
    0.58
    வ்வாறு
    0.56
     देम
    0.54
    哠
    0.53
    aggregation
    0.52
    OLYBD
    0.51
    ็ง
    0.50
     parâmetros
    0.50
    ๗
    0.50
    POSITIVE LOGITS
    Per
    0.84
     PER
    0.81
     Per
    0.80
     Perg
    0.72
     perm
    0.69
     Perce
    0.68
     Perc
    0.67
    Perf
    0.65
    Percy
    0.63
     퍼
    0.61
    Activations Density 0.015%

    No Known Activations