© 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. 64749
    Prev
    Next
    INDEX
    Explanations

    primary care, names, items

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

    primary key assignment

    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
    =\
    0.42
     \
    0.40
     ref
    0.37
    ={
    0.36
     failing
    0.35
     refracting
    0.34
     rescheduled
    0.34
     those
    0.34
     badly
    0.34
     sin
    0.34
    POSITIVE LOGITS
    йс
    0.48
    ஸ்ட்
    0.47
     १७
    0.45
     கண்டுபி
    0.44
     Leclerc
    0.44
     चीज
    0.44
     ﷺ
    0.43
    జాగా
    0.43
     হ্যান
    0.43
     percussion
    0.42
    Activations Density 0.000%

    No Known Activations