© 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. 120638
    Prev
    Next
    INDEX
    Explanations

    ESL support

    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
    <0xE1>
    0.37
     Miche
    0.37
     prag
    0.37
    hecy
    0.37
     LP
    0.36
     Kra
    0.35
    Larry
    0.35
    ահ
    0.35
    堣
    0.35
     Larry
    0.34
    POSITIVE LOGITS
     центре
    0.41
    汾
    0.40
     فيه
    0.39
    +",
    0.39
    !="
    0.39
    Nos
    0.38
    ,",
    0.38
     centerline
    0.38
     시간
    0.37
     দিনের
    0.37
    Activations Density 0.000%

    No Known Activations