© 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. 44594
    Prev
    Next
    INDEX
    Explanations

    present invention

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

    Synopsis, reputation, comfortable, workouts

    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
    över
    0.46
    UNIVERSITY
    0.46
    crits
    0.46
    予防
    0.44
    甙
    0.44
    이랑
    0.43
    ako
    0.43
    dolo
    0.43
    耑
    0.43
    ਾਂ
    0.42
    POSITIVE LOGITS
     câu
    0.44
     curta
    0.44
     posible
    0.44
     incrementally
    0.43
     array
    0.43
     nem
    0.42
     oluştur
    0.42
     curto
    0.42
     parque
    0.42
     Nus
    0.42
    Activations Density 0.002%

    No Known Activations