© 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. 62810
    Prev
    Next
    INDEX
    Explanations

    marks the start of an event

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

    debut or first appearance

    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
    ६
    0.47
    ᴜ
    0.47
     prosegu
    0.47
     reklam
    0.46
    जर
    0.46
    ग
    0.45
    ท
    0.45
    Đ
    0.44
     सुझा
    0.44
     başlayalım
    0.43
    POSITIVE LOGITS
     debut
    0.84
     debuts
    0.77
     деб
    0.73
     डेब्यू
    0.72
    Debut
    0.71
    デビュー
    0.69
    debut
    0.69
     debuted
    0.68
     Debut
    0.67
     debuting
    0.67
    Activations Density 0.029%

    No Known Activations