© 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. 7383
    Prev
    Next
    INDEX
    Explanations

    metrics and ratios

    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
    ួក
    0.67
    ្នាំ
    0.59
    ាតុ
    0.53
    জ্জনক
    0.53
    <unused671>
    0.52
     agrícola
    0.51
     mécanisme
    0.51
    autoconfigure
    0.51
    溶液
    0.50
     automática
    0.49
    POSITIVE LOGITS
     Average
    0.94
     average
    0.86
     Mean
    0.84
     Total
    0.81
     Ratio
    0.79
     평균
    0.76
     %
    0.75
    Average
    0.75
     total
    0.74
     percent
    0.74
    Activations Density 0.021%

    No Known Activations