© 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. 35230
    Prev
    Next
    INDEX
    Explanations

    shape description

    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
     Vou
    0.41
    onto
    0.41
     člov
    0.40
    بن
    0.39
    อร์ต
    0.39
    •
    0.39
    魇
    0.39
     বাই
    0.38
    扃
    0.38
    textFile
    0.38
    POSITIVE LOGITS
     alternate
    0.42
     secondary
    0.41
     tertiary
    0.40
     registry
    0.39
    alternate
    0.38
    ಿಸಿದ್ದ
    0.37
     distant
    0.37
    Alternate
    0.35
     डिल
    0.35
    ອາ
    0.35
    Activations Density 0.000%

    No Known Activations