© 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. 133829
    Prev
    Next
    INDEX
    Explanations

    common word sequences

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

    investment/buy/gamblers/bonuses

    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
    失效
    0.50
     besteht
    0.50
    ー
    0.50
     sienta
    0.50
    ח
    0.50
     overwhelmed
    0.49
     sofort
    0.49
     mogu
    0.48
     ､
    0.48
    alámb
    0.47
    POSITIVE LOGITS
    startGame
    0.50
     bonuses
    0.47
     gamblers
    0.45
    <?
    0.44
    राउंड
    0.44
    hits
    0.43
     यूं
    0.43
    pics
    0.42
    หุ้น
    0.42
     tremend
    0.42
    Activations Density 0.001%

    No Known Activations