© 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. 145096
    Prev
    Next
    INDEX
    Explanations

    without adequate knowledge

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

    Foreign investment, care, and duplex communication

    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
    ’
    0.50
    Door
    0.49
     Appetite
    0.46
     رای
    0.46
     banyak
    0.45
    ม
    0.43
    ure
    0.43
     துவ
    0.43
     Door
    0.43
     ببین
    0.43
    POSITIVE LOGITS
     tathapi
    0.54
     phony
    0.50
     教
    0.46
    Predicate
    0.46
     gamanam
    0.46
     subpar
    0.45
    ための
    0.45
    warl
    0.45
    нец
    0.45
    hä
    0.44
    Activations Density 0.002%

    No Known Activations