© 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. 63945
    Prev
    Next
    INDEX
    Explanations

    concepts joined by ampersand

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

    Digital marketing, Christian, warfare, hesitate

    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
    ﾎ
    0.55
    _
    0.54
    一個
    0.49
    下
    0.49
    一个
    0.48
    __'
    0.48
    OGRAM
    0.47
    ﾁ
    0.46
    MathClass
    0.46
    一下
    0.45
    POSITIVE LOGITS
     difíciles
    0.55
     Dominik
    0.53
     menyes
    0.50
     izdel
    0.49
     slightest
    0.48
     ഇഷ്ട
    0.47
     scarves
    0.47
     مواد
    0.46
     materiali
    0.46
     skipper
    0.46
    Activations Density 0.000%

    No Known Activations