© 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. 201292
    Prev
    Next
    INDEX
    Explanations

    younger population

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

    cooling, ending in "are", "in", "a"

    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
    юсь
    0.59
    좀
    0.54
    ття
    0.48
    ה
    0.48
    тона
    0.47
    이번
    0.47
    ב
    0.46
    이트
    0.46
     내가
    0.46
    нула
    0.46
    POSITIVE LOGITS
    rav
    0.45
     ধর্মের
    0.43
    ül
    0.42
     clickable
    0.42
     dowol
    0.42
     giản
    0.41
     isten
    0.41
     širo
    0.40
    ved
    0.39
    શ્ર
    0.39
    Activations Density 0.001%

    No Known Activations