© 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. 41464
    Prev
    Next
    INDEX
    Explanations

    888 casino, exchange, dad, housing

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

    uncertainty and questions

    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
     realizadas
    0.48
     नाराज
    0.46
    里
    0.45
    查
    0.44
    嘲
    0.44
    сю
    0.44
     addressed
    0.43
    觉
    0.43
    щения
    0.42
    с
    0.42
    POSITIVE LOGITS
     เด็ก
    0.51
     stator
    0.48
    രുവന
    0.46
     آمریک
    0.46
     কমান্ড
    0.46
     eixo
    0.45
     น้ำ
    0.43
     성능
    0.43
     ہے۔
    0.43
     ファイル
    0.43
    Activations Density 0.001%

    No Known Activations