© 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. 211425
    Prev
    Next
    INDEX
    Explanations

    state of emergency

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

    generation

    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
     겨
    0.50
     tetahi
    0.50
    Ⅰ
    0.49
     অর্চন
    0.48
     తొలి
    0.48
     できる
    0.48
     ကျွန်
    0.48
     œufs
    0.46
     শরত
    0.46
     ผม
    0.46
    POSITIVE LOGITS
    телно
    0.42
    Released
    0.42
    ⏰
    0.41
    тел
    0.40
     یونیورسٹی
    0.38
    UNIVERS
    0.38
    TV
    0.38
    Minutes
    0.38
    Barcode
    0.38
     smacked
    0.37
    Activations Density 0.000%

    No Known Activations