© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 61373
    Prev
    Next
    INDEX
    Explanations

    basic unit

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ộm
    0.46
    पोरेशन
    0.42
    ‘
    0.42
     प्रतीक्षा
    0.41
    Getenv
    0.41
    viper
    0.40
    ERRORTYPE
    0.40
    salaryfrom
    0.40
    قیه
    0.39
    淈
    0.39
    POSITIVE LOGITS
     unit
    2.14
     units
    1.92
    unit
    1.85
    Unit
    1.80
     Unit
    1.78
    单位
    1.74
    単位
    1.74
    units
    1.70
     Units
    1.70
     unidad
    1.68
    Activations Density 0.006%

    No Known Activations