© 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-65K
    7. 13176
    Prev
    Next
    INDEX
    Explanations

    website links and titles

    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_65k_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
    <0xC2>
    0.45
    aju
    0.43
    OCK
    0.42
     रेट
    0.41
    IDAY
    0.41
     زیرمه
    0.41
    เคล
    0.41
    alade
    0.39
     curated
    0.38
    át
    0.38
    POSITIVE LOGITS
     ~$
    0.39
     বুঝ
    0.38
     Dow
    0.38
     Secondary
    0.37
     -,
    0.36
     ол
    0.35
     paramilitary
    0.35
     five
    0.35
     SAS
    0.35
     অধ
    0.34
    Activations Density 0.006%

    No Known Activations