© 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. 219156
    Prev
    Next
    INDEX
    Explanations

    alchemist, Siddhartha, don Juan, Diaries, Yerba mate

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

    cooking and invention terms

    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
    5
    0.83
    8
    0.79
    7
    0.76
    4
    0.72
    3
    0.67
    6
    0.67
    0
    0.61
    2
    0.59
    $
    0.58
    9
    0.58
    POSITIVE LOGITS
    鳧
    0.48
     آز
    0.46
    িশালী
    0.46
     ویکی‌پ
    0.45
     روسی
    0.45
     Elektrokhimiya
    0.44
     pwm
    0.44
     또한
    0.44
     الكهرب
    0.44
    也在
    0.43
    Activations Density 0.005%

    No Known Activations