© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4047
    Prev
    Next
    INDEX
    Explanations

    verbs of action and management

    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_16_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
    ct
    0.34
    de
    0.33
    th
    0.32
     \
    0.32
     be
    0.32
     strengthen
    0.32
     de
    0.31
     revitalize
    0.30
    ক
    0.30
     liberate
    0.30
    POSITIVE LOGITS
    い
    0.30
     Muhammadu
    0.29
    mäss
    0.28
     Gä
    0.28
    ו
    0.28
    おお
    0.27
     samman
    0.27
    an
    0.27
    ið
    0.27
    這些
    0.26
    Activations Density 0.506%

    No Known Activations