© 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. 113098
    Prev
    Next
    INDEX
    Explanations

    same hold, new YouTube, PS3 version

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

    training data cutoff

    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
    ajaan
    0.52
    centi
    0.49
    esterday
    0.48
    ড়ি
    0.48
    菸
    0.48
     продукти
    0.47
    意味
    0.47
    ピング
    0.47
    candles
    0.47
    商品
    0.47
    POSITIVE LOGITS
     $\
    0.48
     $|\
    0.46
     intermittently
    0.43
    _{-
    0.43
     ويمكن
    0.42
     NASA
    0.41
     अभिक्रिया
    0.41
     $|
    0.39
     rerun
    0.39
     Future
    0.39
    Activations Density 0.000%

    No Known Activations