© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2185
    Prev
    Next
    INDEX
    Explanations

    variable and code constructs

    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
    lovepoetry
    0.27
     calomel
    0.27
     antigenic
    0.27
     $(`.
    0.27
     miso
    0.26
     antigens
    0.26
     quinine
    0.26
     secretions
    0.26
     estím
    0.26
     spasm
    0.26
    POSITIVE LOGITS
    0
    0.34
    and
    0.33
    G
    0.31
    Use
    0.30
    A
    0.30
    4
    0.30
    А
    0.30
    In
    0.30
    2
    0.30
    AI
    0.29
    Activations Density 1.414%

    No Known Activations