© 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. 95673
    Prev
    Next
    INDEX
    Explanations

    Hindu would

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

    double-slit experiment

    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
     τρόπο
    0.50
    λό
    0.49
     ডলার
    0.48
    钱
    0.47
     డబ్బు
    0.44
    ड़ाई
    0.43
    ább
    0.42
    吃饭
    0.42
    द्योगिकी
    0.42
    规划
    0.42
    POSITIVE LOGITS
     alle
    0.49
     Vs
    0.49
     oxen
    0.49
     (~
    0.48
     abhis
    0.47
     consoles
    0.47
     millis
    0.46
     speciali
    0.46
     magar
    0.46
     alcanz
    0.45
    Activations Density 0.001%

    No Known Activations