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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222561
    Prev
    Next
    INDEX
    Explanations

    system performance

    np_acts-logits-general · gemini-2.5-flash-lite

    using tools to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accuracy
    0.50
    ‌.
    0.50
    Structure
    0.47
    ITERATURE
    0.45
    Storage
    0.45
    .",[
    0.45
    Baked
    0.45
    Nin
    0.44
    Nicht
    0.44
    Finger
    0.44
    POSITIVE LOGITS
     ਲਈ
    0.52
    s
    0.51
     απ
    0.48
     Jacobsen
    0.47
     पक्षा
    0.47
     ਆ
    0.47
     χ
    0.46
     ਦੇ
    0.46
     lucid
    0.46
     op
    0.46
    Activations Density 0.000%

    No Known Activations