© 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. 19937
    Prev
    Next
    INDEX
    Explanations

    hyperlink

    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
    нг
    0.51
     Έ
    0.50
     ит
    0.49
    자
    0.48
     Rá
    0.48
     ਉਹ
    0.47
    א
    0.47
     Кар
    0.45
    ❧
    0.45
     Exxon
    0.45
    POSITIVE LOGITS
    JSON
    0.52
     içinde
    0.49
     fitur
    0.48
    maty
    0.48
    UID
    0.48
     features
    0.47
     functionality
    0.46
    TUN
    0.46
    FINED
    0.46
     behavior
    0.45
    Activations Density 0.002%

    No Known Activations