© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    lists ending in "All"

    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
    ،
    0.46
     (
    0.36
    、
    0.36
     sajana
    0.35
    FA
    0.35
     والذي
    0.35
    ，
    0.34
     -
    0.34
     Doremi
    0.33
    I
    0.33
    POSITIVE LOGITS
     thậm
    0.38
    е
    0.37
    ū
    0.35
     hues
    0.35
     volcanoes
    0.35
     humains
    0.35
    یا
    0.34
     cyclones
    0.34
    ın
    0.34
     microbes
    0.34
    Activations Density 2.080%

    No Known Activations