© 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. 97015
    Prev
    Next
    INDEX
    Explanations

    human host, medical students, Fox News, waste collection

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

    kings and AI plugins

    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
     fn
    0.44
    yun
    0.44
     leven
    0.43
    ieel
    0.41
    ([[
    0.41
     result
    0.40
     totaled
    0.40
     Too
    0.40
    ackel
    0.40
     Murphy
    0.39
    POSITIVE LOGITS
     Сер
    0.62
     ইতিহাসের
    0.50
    interactions
    0.48
    སྐ
    0.47
    ཚ
    0.47
     acest
    0.47
    policies
    0.47
     この
    0.46
     Эти
    0.46
     이러한
    0.45
    Activations Density 0.008%

    No Known Activations