© 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. 152416
    Prev
    Next
    INDEX
    Explanations

    requirements, annual, nervous, handle

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

    while discussing research

    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
    Ан
    0.49
    ଫ
    0.46
     अभिकारक
    0.45
    фо
    0.44
    REACTOR
    0.44
     system
    0.44
     sorption
    0.44
    EnumType
    0.44
    新鮮
    0.43
    ন্ত্রণাল
    0.43
    POSITIVE LOGITS
     Coastal
    0.52
    TOTAL
    0.49
    orde
    0.48
    lando
    0.47
     &=\
    0.47
    롤
    0.46
    includ
    0.45
    cciones
    0.45
     inmediato
    0.45
    radas
    0.43
    Activations Density 0.001%

    No Known Activations