© 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. 139290
    Prev
    Next
    INDEX
    Explanations

    Everyday Italian

    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
    committees
    0.48
    ﾗ
    0.46
    ুদ্র
    0.45
    াস
    0.45
    绉
    0.44
    ై
    0.44
    ᇁ
    0.44
    শাসন
    0.43
     alluvial
    0.43
     blocker
    0.43
    POSITIVE LOGITS
     Excell
    0.44
     treści
    0.42
     swag
    0.42
     Supporters
    0.42
    특별
    0.40
     sofistic
    0.40
    formatted
    0.39
     jeżeli
    0.39
    ++++
    0.39
     SWOT
    0.38
    Activations Density 0.005%

    No Known Activations