© 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. 159749
    Prev
    Next
    INDEX
    Explanations

    sales tax for orders

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

    of results

    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
     अहंकार
    0.46
     tranquillity
    0.43
    G
    0.42
     बंदी
    0.40
    bikes
    0.40
    guards
    0.40
     जमान
    0.40
    J
    0.40
     planing
    0.39
     گرفتار
    0.39
    POSITIVE LOGITS
    Dados
    0.49
     náz
    0.47
    篠
    0.46
    ילו
    0.45
     נע
    0.43
    ্য
    0.43
    лії
    0.42
    פי
    0.42
    ”),
    0.41
     neurologist
    0.41
    Activations Density 0.000%

    No Known Activations