© 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. 96262
    Prev
    Next
    INDEX
    Explanations

    time or duration

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

    legal and safe solutions

    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
    TCP
    0.50
    Taylor
    0.47
    AMP
    0.46
    FLD
    0.46
    STTS
    0.45
    녁
    0.45
    Flex
    0.45
    HTTP
    0.44
    JAVA
    0.43
    VEST
    0.43
    POSITIVE LOGITS
     ஓய்
    0.55
     एक्सचेंज
    0.50
     considerato
    0.46
    borderwidth
    0.46
     अफेयर
    0.46
     abit
    0.45
    ز
    0.45
    قة
    0.45
     થો
    0.44
    േരി
    0.44
    Activations Density 0.000%

    No Known Activations