© 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. 145217
    Prev
    Next
    INDEX
    Explanations

    4th century invention

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

    foreign words and phrases

    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
     founding
    0.55
    י
    0.49
    collapse
    0.48
     colony
    0.48
    ית
    0.46
    quoia
    0.45
     initialise
    0.44
     cladding
    0.44
    ৬৮
    0.43
    愼
    0.43
    POSITIVE LOGITS
     результата
    0.52
    oot
    0.48
     Rowing
    0.47
     ude
    0.46
     vissa
    0.46
     Odd
    0.44
     rå
    0.44
     Towers
    0.44
     Wages
    0.44
     Jodi
    0.43
    Activations Density 0.001%

    No Known Activations