© 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. 127944
    Prev
    Next
    INDEX
    Explanations

    meal, market, owners, charts, referenced, funds, Property, City, different

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

    technical online information jargon

    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
     מר
    0.55
     المطلوب
    0.52
     શ્રી
    0.52
     חש
    0.51
    .|__
    0.50
     дам
    0.50
    ﭜ
    0.50
     रोटी
    0.49
     מב
    0.49
     автомоби
    0.48
    POSITIVE LOGITS
    ल्ल्या
    0.48
     Burch
    0.48
     Prok
    0.47
    嵋
    0.46
     diagon
    0.45
     a
    0.45
    kte
    0.45
     Brahmin
    0.45
    plasma
    0.45
    大陸
    0.44
    Activations Density 0.000%

    No Known Activations