© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99699
    Prev
    Next
    INDEX
    Explanations

    instances, test, learning, feedback, inclusion

    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_31_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
    ால
    0.52
     xaxis
    0.47
    笂
    0.47
    垪
    0.46
    罗
    0.46
    莯
    0.44
    ალი
    0.44
    Au
    0.44
    ็ก
    0.43
    Ꮽ
    0.43
    POSITIVE LOGITS
    bie
    0.47
     غير
    0.42
     Marathi
    0.42
     販売
    0.40
     running
    0.40
     BI
    0.40
    namese
    0.40
     workbook
    0.40
    ndrome
    0.39
     NM
    0.39
    Activations Density 0.006%

    No Known Activations