© 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. 102151
    Prev
    Next
    INDEX
    Explanations

    God shouted for joy

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

    geometric alignment

    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
    sen
    0.52
    ILLIPS
    0.46
    }$\
    0.45
    system
    0.44
    kette
    0.43
    $\
    0.43
    }~\
    0.42
    suc
    0.42
     конди
    0.42
    decine
    0.41
    POSITIVE LOGITS
     Invention
    0.47
    cardia
    0.47
     Apartments
    0.46
     প্রকল্পটি
    0.45
     Malgré
    0.44
     invention
    0.44
    ασία
    0.43
     mairie
    0.43
    剡
    0.43
     bâtiment
    0.42
    Activations Density 0.002%

    No Known Activations