© 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. 40442
    Prev
    Next
    INDEX
    Explanations

    excessive on, real red

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

    various food and health terms

    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
     accomplishes
    0.50
     accomplish
    0.48
     stai
    0.46
    раб
    0.42
    لية
    0.39
     pretrial
    0.39
    ὅ
    0.39
    ве
    0.39
     transformer
    0.39
     powod
    0.38
    POSITIVE LOGITS
     JavaBean
    0.52
     diarrhoea
    0.50
     yoghurt
    0.48
     HttpSession
    0.47
     savoury
    0.47
     JavaBeans
    0.46
    不愿意
    0.46
     నిషే
    0.46
     bureaux
    0.45
    gmzy
    0.45
    Activations Density 0.000%

    No Known Activations