© 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. 26833
    Prev
    Next
    INDEX
    Explanations

    Python typing and syntax

    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
    ),\\
    0.43
    umas
    0.40
    bour
    0.40
    wati
    0.39
    ਠ
    0.39
    ]\\
    0.39
    ਣਾ
    0.38
    ,\\
    0.38
    ENTAL
    0.38
    boundaries
    0.38
    POSITIVE LOGITS
     datac
    0.57
    🫶
    0.51
     typing
    0.51
     async
    0.50
     FastAPI
    0.50
    🫠
    0.50
     PEP
    0.50
    PEP
    0.47
    datac
    0.47
     Typing
    0.47
    Activations Density 0.003%

    No Known Activations