© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88213
    Prev
    Next
    INDEX
    Explanations

    B-tree,TreeMap,ball bearings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ilmu
    0.63
    ﺘ
    0.63
     بی
    0.62
     ພວກເຮົາ
    0.62
    ﻮ
    0.62
    ﺤ
    0.62
    ﺭ
    0.61
     antena
    0.59
     Valores
    0.59
    present
    0.58
    POSITIVE LOGITS
    ı
    0.75
    ä
    0.66
    ë
    0.65
    路的
    0.63
    客服
    0.60
    所以
    0.59
    æ
    0.57
    ç
    0.57
    }\{\
    0.56
    äst
    0.55
    Activations Density 0.003%

    No Known Activations