© 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. 163136
    Prev
    Next
    INDEX
    Explanations

    what we give

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

    very fast | dominate | constant bus | cumming | critical | yes or no

    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
    ylan
    0.48
    į
    0.48
    âl
    0.47
    ifice
    0.46
    ግሎ
    0.46
     naissance
    0.45
     façon
    0.45
    ட்ப
    0.45
    ⚔
    0.45
    ethylamine
    0.43
    POSITIVE LOGITS
     Common
    0.52
     Female
    0.49
     Voluntary
    0.48
     Open
    0.47
    ायर
    0.46
     Comprehensive
    0.46
     Outdoor
    0.46
     Working
    0.46
     Aquarium
    0.45
     usc
    0.45
    Activations Density 0.000%

    No Known Activations