© 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. 223235
    Prev
    Next
    INDEX
    Explanations

    Russian technical words

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

    Foundation

    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
    uj
    0.47
     które
    0.45
     concentrate
    0.45
     lle
    0.45
     riverside
    0.44
     p
    0.44
     cada
    0.44
     penultimate
    0.43
     तब
    0.43
     continuamente
    0.43
    POSITIVE LOGITS
    леп
    0.55
    学院
    0.50
    дования
    0.49
    ясь
    0.49
    лися
    0.48
    டிப்ப
    0.48
    婆
    0.47
    кали
    0.47
    дование
    0.46
    秃
    0.46
    Activations Density 0.003%

    No Known Activations