© 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. 104334
    Prev
    Next
    INDEX
    Explanations

    reports, specific, Dr, Methodology, Boolean, PS

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

    titles Chief Officer

    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
    ęb
    0.52
    졍
    0.50
     Tram
    0.48
     شہید
    0.46
    льним
    0.46
    alleng
    0.45
    בור
    0.45
     prawd
    0.45
    調べ
    0.44
    생
    0.43
    POSITIVE LOGITS
     قطعة
    0.52
     минуты
    0.51
     يُ
    0.48
     учиты
    0.47
     разрабо
    0.46
     минуту
    0.46
    FULLY
    0.45
     конфигура
    0.45
     अधिसू
    0.45
     полноцен
    0.45
    Activations Density 0.000%

    No Known Activations