© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    New Zealand

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

    task completion and suggestions

    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
    軞
    0.36
    "+"|".
    0.36
    <unused27>
    0.33
    tDBOutput
    0.33
    齑
    0.33
    <unused24>
    0.32
    ೬
    0.32
     فيدي
    0.32
    ৯
    0.32
    ೪
    0.32
    POSITIVE LOGITS
    0.34
     first
    0.30
     primeiro
    0.30
     primeira
    0.29
    ↵
    0.28
    Cur
    0.28
    ↵↵
    0.27
     M
    0.27
    Arc
    0.27
    C
    0.27
    Activations Density 0.017%

    No Known Activations