© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    numbers and dollar amounts

    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
    ad
    0.49
     MAPK
    0.44
    ↵↵
    0.43
     Andrew
    0.43
     Scene
    0.43
     Huge
    0.42
     K
    0.42
     Where
    0.42
     Où
    0.41
     Island
    0.41
    POSITIVE LOGITS
    в
    0.53
    nement
    0.50
    0
    0.50
    ри
    0.49
    、《
    0.49
    are
    0.49
    l
    0.48
    ן
    0.48
    見
    0.47
     کي
    0.46
    Activations Density 0.092%

    No Known Activations