© 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. 154243
    Prev
    Next
    INDEX
    Explanations

    caused by Mosque

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

    parameters as knobs

    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
    ंचल
    0.49
    #
    0.47
     खाद
    0.42
    #,
    0.42
     Счет
    0.41
     Biochem
    0.41
     Nutr
    0.41
     अपने
    0.40
    #.
    0.40
     dụng
    0.40
    POSITIVE LOGITS
    müş
    0.51
    joe
    0.46
    ۹
    0.45
    閪
    0.45
    irmingham
    0.44
    ğun
    0.44
     mää
    0.44
    lardan
    0.43
     SAME
    0.43
     마찬가지
    0.43
    Activations Density 0.000%

    No Known Activations