© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13782
    Prev
    Next
    INDEX
    Explanations

    number followed by a word

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

    bruise, brush,

    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_16k_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
    =========
    0.46
    Argument
    0.43
    ৌক
    0.43
     argomento
    0.43
    Promo
    0.43
    usega
    0.41
    Show
    0.40
    Review
    0.40
    custom
    0.39
    Online
    0.39
    POSITIVE LOGITS
     टेट
    0.41
     контра
    0.37
     大人
    0.37
     "$"
    0.37
     lute
    0.37
     пли
    0.37
    コント
    0.36
     ட
    0.36
     ui
    0.35
    カード
    0.35
    Activations Density 0.262%

    No Known Activations