© 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. 44354
    Prev
    Next
    INDEX
    Explanations

    reading text or files

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

    StreamReader and StreamWriter

    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
     vêtements
    0.45
     شدند
    0.43
    ชุด
    0.42
    บ่ง
    0.42
     haircuts
    0.42
    curricular
    0.42
    탤
    0.42
    టన
    0.41
     roupas
    0.41
    Вакан
    0.40
    POSITIVE LOGITS
     الهواء
    0.46
     water
    0.43
     آب
    0.42
     Tiber
    0.42
     реки
    0.42
     nước
    0.42
     InputStream
    0.42
     phosphoric
    0.41
     مساء
    0.41
     воду
    0.41
    Activations Density 0.000%

    No Known Activations