© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69539
    Prev
    Next
    INDEX
    Explanations

    compound words

    np_acts-logits-general · gemini-2.5-flash-lite

    attached to reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yta
    0.49
    仼
    0.48
    你
    0.46
    刻
    0.45
    当时
    0.45
    ått
    0.44
    欠
    0.44
    我们
    0.43
    વારે
    0.43
    上海
    0.43
    POSITIVE LOGITS
     chest
    0.59
     winner
    0.55
     pectoral
    0.53
     bikini
    0.52
     kulit
    0.52
     pelvic
    0.51
     skirting
    0.51
     green
    0.50
     platelet
    0.50
     ننوت
    0.49
    Activations Density 0.001%

    No Known Activations