© 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. 170135
    Prev
    Next
    INDEX
    Explanations

    titles and arrivals

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

    categorizing, less frequent to dramatic

    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
     सफाई
    0.46
     δύο
    0.45
     HOTEL
    0.45
     vài
    0.44
     ሕ
    0.43
     other
    0.43
     crumbs
    0.42
     판단
    0.42
     ଗ
    0.42
     মূর্তি
    0.41
    POSITIVE LOGITS
    ابقه
    0.48
     vicino
    0.46
     integrates
    0.45
     accelerates
    0.44
    formerly
    0.43
    ظر
    0.43
    திலும்
    0.43
    جهزة
    0.42
    णाली
    0.42
     proporciona
    0.41
    Activations Density 0.001%

    No Known Activations