© 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. 178025
    Prev
    Next
    INDEX
    Explanations

    production stages, oil revenue, chains

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

    understanding complex systems

    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
     penulis
    0.47
     veteran
    0.46
    incidence
    0.46
     ۳
    0.45
    ัน
    0.44
     looming
    0.44
    yección
    0.44
    ய
    0.43
     crushing
    0.42
     असा
    0.42
    POSITIVE LOGITS
    trp
    0.54
    uut
    0.50
     देम
    0.48
    asr
    0.48
     Bedien
    0.47
    多种
    0.46
    ToSort
    0.46
     ofApp
    0.46
    蛔
    0.46
    Herk
    0.45
    Activations Density 0.001%

    No Known Activations