© 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. 60958
    Prev
    Next
    INDEX
    Explanations

    specific words and punctuation

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

    recent recent recent

    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
     premières
    0.49
     cages
    0.48
    @@]
    0.48
     :-)
    0.47
     हाउ
    0.47
     kebakaran
    0.47
    icester
    0.46
     cage
    0.46
    illage
    0.46
     приложения
    0.45
    POSITIVE LOGITS
    recent
    0.57
    Recent
    0.54
    ب
    0.53
    فظ
    0.52
    ت
    0.52
    BackgroundColor
    0.52
    ل
    0.52
    backs
    0.51
    고
    0.50
     بيان
    0.50
    Activations Density 0.000%

    No Known Activations