© 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. 22545
    Prev
    Next
    INDEX
    Explanations

    a lot of information

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

    import string, time

    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
    Jogador
    0.42
     subtração
    0.40
    ossing
    0.40
    कुल
    0.39
    ißler
    0.39
    बर्ट
    0.38
    ‰
    0.37
    សុ
    0.37
     swells
    0.36
    🙇
    0.36
    POSITIVE LOGITS
     Lifetime
    0.46
     evidence
    0.40
     Dairy
    0.39
     City
    0.39
    اقات
    0.38
     civile
    0.38
     Diary
    0.38
     co
    0.37
     Civilian
    0.37
    تر
    0.37
    Activations Density 0.001%

    No Known Activations