© 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. 224684
    Prev
    Next
    INDEX
    Explanations

    consumption, ROI, lighter, mountains, way, laughing

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

    avoid, impossible, controversial, dated

    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
     함수
    0.50
     खिलाड़ियों
    0.50
    میل
    0.50
     Функция
    0.50
    τη
    0.49
     항
    0.47
     Personalized
    0.47
     Counts
    0.47
     확인
    0.46
    ファイルの
    0.46
    POSITIVE LOGITS
    <0x96>
    0.48
     genug
    0.46
     prag
    0.42
     ekst
    0.42
     reconsider
    0.42
     konsult
    0.41
    ج
    0.41
     creativity
    0.41
     dokument
    0.41
     heli
    0.40
    Activations Density 0.000%

    No Known Activations