© 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. 130399
    Prev
    Next
    INDEX
    Explanations

    car details and filings

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

    sector A

    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
     podmín
    0.48
    Парт
    0.47
    PRODUCTS
    0.46
    RULES
    0.46
    Adress
    0.44
    坯
    0.44
    FORM
    0.44
    蚁
    0.43
    <0x94>
    0.43
    ële
    0.43
    POSITIVE LOGITS
     spreading
    0.49
     invigorating
    0.49
     tapering
    0.48
     flexing
    0.47
     exercising
    0.46
     ಮಾಹಿತಿ
    0.46
     fighting
    0.46
     translating
    0.45
     articulo
    0.44
     occupying
    0.43
    Activations Density 0.002%

    No Known Activations