© 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. 248630
    Prev
    Next
    INDEX
    Explanations

    Android Auto

    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
     ◆
    0.50
    GEN
    0.48
    人們
    0.46
     Armada
    0.46
     विरोध
    0.45
     ग्रामीण
    0.44
    เทพ
    0.44
    matis
    0.43
     Statutory
    0.43
     फायरिंग
    0.43
    POSITIVE LOGITS
     akik
    0.49
    ولة
    0.46
    acağı
    0.44
    -]
    0.44
     саны
    0.43
     microSD
    0.42
     marrying
    0.42
    azaar
    0.42
    aln
    0.41
     кто
    0.41
    Activations Density 0.000%

    No Known Activations