© 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. 202338
    Prev
    Next
    INDEX
    Explanations

    Home » followed by category

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

    mathematical and technical 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
    painting
    0.50
     الوا
    0.49
    3
    0.49
    ato
    0.48
    أ
    0.48
    uno
    0.47
    ت
    0.47
    Stand
    0.46
    بر
    0.45
    4
    0.45
    POSITIVE LOGITS
     삭제
    0.62
     gimm
    0.54
     sht
    0.53
     무게
    0.53
     컬
    0.52
     확장
    0.51
    
    0.51
     моди
    0.49
     문제가
    0.49
     요거
    0.48
    Activations Density 0.000%

    No Known Activations