© 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. 6740
    Prev
    Next
    INDEX
    Explanations

    one sentence summary

    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
     we
    0.50
    we
    0.47
    We
    0.46
    He
    0.44
    bp
    0.44
    f
    0.43
    frequency
    0.42
    TABLE
    0.41
    Мы
    0.41
    ad
    0.39
    POSITIVE LOGITS
     Kommun
    0.55
     Intelig
    0.51
     Gin
    0.47
    <unused423>
    0.45
     Audubon
    0.45
    <unused332>
    0.45
     क्रमवारीत
    0.44
     Convertible
    0.44
    <unused182>
    0.43
     Investigative
    0.43
    Activations Density 0.003%

    No Known Activations