© 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. 122833
    Prev
    Next
    INDEX
    Explanations

    as much, subsystem in, other wire

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

    complex medical installation

    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
     byen
    0.45
     kendine
    0.44
    );\
    0.44
     singer
    0.44
    ಲಿದೆ
    0.44
     disseminate
    0.43
     maintains
    0.43
     finans
    0.43
     /><
    0.43
     kandid
    0.42
    POSITIVE LOGITS
    т
    0.45
    لعاب
    0.43
    ين
    0.41
    。」
    0.41
    ப்புக
    0.41
     ډول
    0.40
     sometimes
    0.40
     배열
    0.40
    Sometimes
    0.40
     Sometimes
    0.39
    Activations Density 0.001%

    No Known Activations