© 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. 164552
    Prev
    Next
    INDEX
    Explanations

    consider your

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

    modular arithmetic

    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
    ק
    0.50
     gstlal
    0.50
     호텔
    0.49
     분포
    0.49
    닮
    0.47
    ịa
    0.46
    к
    0.46
    മുണ്ട്
    0.46
     අවශ්‍ය
    0.46
     不过
    0.45
    POSITIVE LOGITS
    '
    0.52
    飭
    0.46
     fic
    0.43
     verso
    0.42
     dev
    0.41
    endev
    0.41
     DX
    0.41
     XB
    0.41
     XS
    0.41
     sweeping
    0.40
    Activations Density 0.000%

    No Known Activations