© 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. 44987
    Prev
    Next
    INDEX
    Explanations

    cultures in and do you

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

    scale and size

    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
    ဖြင့်
    0.48
    acji
    0.47
     मूवमेंट
    0.46
    katore
    0.45
    ラリー
    0.44
    籁
    0.44
    େ
    0.43
    цією
    0.43
    NIK
    0.42
     หน้า
    0.42
    POSITIVE LOGITS
     epub
    0.47
     establecida
    0.46
     hecha
    0.46
     tercer
    0.44
     ese
    0.43
     parip
    0.43
     todavía
    0.43
    ।)
    0.43
     ///
    0.42
     originalmente
    0.42
    Activations Density 0.000%

    No Known Activations