© 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. 208672
    Prev
    Next
    INDEX
    Explanations

    cultural organization, report, controlled temperature, jersey, developed, create, DUI, send signals

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

    legal consequences and ramifications

    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
     inoculated
    0.47
    ائن
    0.45
     எட்டு
    0.45
     DeConcini
    0.45
    ाना
    0.44
    ,"@
    0.43
     injurious
    0.43
     ©️
    0.42
    मर्रा
    0.42
     سلاټ
    0.42
    POSITIVE LOGITS
     BOW
    0.48
    Cities
    0.47
    pu
    0.47
     者
    0.44
     turist
    0.44
    BOW
    0.44
    pero
    0.43
    pbs
    0.43
    but
    0.43
    mi
    0.42
    Activations Density 0.000%

    No Known Activations