© 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. 105808
    Prev
    Next
    INDEX
    Explanations

    checklist completions and conditional actions

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

    Taxes Don't Fund Spending

    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
    灶
    0.50
    لاھ
    0.48
    废物
    0.46
    بوع
    0.46
    conten
    0.45
    باز
    0.45
    kurs
    0.44
    語言
    0.44
    폿
    0.44
    보면
    0.42
    POSITIVE LOGITS
    ），
    0.49
     '')
    0.48
     秒
    0.47
     eyelashes
    0.46
     கல
    0.44
     diphenyl
    0.44
     어렵
    0.44
     COVID
    0.44
     composite
    0.43
     exquisite
    0.43
    Activations Density 0.001%

    No Known Activations