© 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. 17482
    Prev
    Next
    INDEX
    Explanations

    numbers and specific nouns

    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
     seduced
    0.33
     замены
    0.30
    (.*
    0.29
     வகைகள்
    0.29
     **,
    0.28
     ব্যপারে
    0.28
    퐶
    0.28
     മേഖ
    0.28
    🔸
    0.28
    퀀
    0.28
    POSITIVE LOGITS
    0.43
    )
    0.41
    ↵
    0.35
     be
    0.35
     is
    0.33
     has
    0.32
     to
    0.31
    的
    0.30
    」
    0.30
    .
    0.30
    Activations Density 0.351%

    No Known Activations