© 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. 40-GEMMASCOPE-2-RES-262K
    7. 641
    Prev
    Next
    INDEX
    Explanations

    inputenc specification

    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_40_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
     فونٹ
    0.36
    蒨
    0.35
    뇰
    0.35
     onPressed
    0.34
    ইংরেজি
    0.34
    🥖
    0.34
    🇬
    0.34
     पिंडदान
    0.34
     डिजी
    0.33
     ভাষার
    0.33
    POSITIVE LOGITS
    Input
    0.40
     input
    0.39
    rir
    0.35
    &
    0.34
     Input
    0.34
    insen
    0.33
    input
    0.32
    mt
    0.32
    len
    0.31
     pub
    0.31
    Activations Density 0.000%

    No Known Activations