© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123595
    Prev
    Next
    INDEX
    Explanations

    truck despiteone ofsaid ,They movedoscill scopeswants ourlocal orroom ,he fixedHe warned

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

    Gemini AI and ethical considerations

    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
    i
    0.50
    2
    0.47
    7
    0.47
    voli
    0.46
    empirical
    0.46
    Doc
    0.46
    3
    0.46
    лі
    0.45
    協議
    0.44
    <0xBA>
    0.44
    POSITIVE LOGITS
     प्रसन्न
    0.48
     permeates
    0.48
     dashboards
    0.46
     进入
    0.46
     penetrates
    0.46
     allergens
    0.44
     attendants
    0.44
     industriales
    0.44
     गुरूवार
    0.44
     emble
    0.44
    Activations Density 0.000%

    No Known Activations