© 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. 210713
    Prev
    Next
    INDEX
    Explanations

    bracketed phrases

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

    end of phrase punctuation

    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
     be
    0.77
    {
    0.67
     cambi
    0.60
    )。
    0.60
     have
    0.59
     (
    0.57
    have
    0.57
    (
    0.57
    ז
    0.55
    (&
    0.55
    POSITIVE LOGITS
     червня
    0.67
    реи
    0.66
    कांग्रेस
    0.64
    Με
    0.63
    Ме
    0.61
    Бе
    0.60
    Một
    0.59
    Как
    0.57
    ل
    0.57
    魄
    0.57
    Activations Density 1.144%

    No Known Activations