© 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. 247627
    Prev
    Next
    INDEX
    Explanations

    definitions, Income, taxes

    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
     bioinformatics
    0.47
    实际上
    0.45
     bakın
    0.44
    乔
    0.44
    总之
    0.43
    鱿
    0.43
    英国
    0.43
     दरअसल
    0.43
    美国
    0.42
    麸
    0.41
    POSITIVE LOGITS
     الكلام
    0.46
     estacion
    0.43
    SERVIDOR
    0.42
     كلام
    0.42
    спекти
    0.42
     blankets
    0.41
    ICIAL
    0.41
    lings
    0.41
    mets
    0.40
     Income
    0.40
    Activations Density 0.000%

    No Known Activations