© 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. 197789
    Prev
    Next
    INDEX
    Explanations

    about other people

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

    Encourage appropriate

    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
     مدارس
    0.52
     መሳሪያ
    0.51
     سبتمبر
    0.48
     अना
    0.48
     ठ
    0.47
     ショルダー
    0.47
     écoles
    0.47
     மணியே
    0.46
     अक्षर
    0.46
     الاطلاع
    0.46
    POSITIVE LOGITS
    '
    0.49
    प्रोड
    0.49
    บน
    0.47
    çok
    0.47
    full
    0.46
     penuh
    0.44
    on
    0.44
     housing
    0.44
    carboxylic
    0.44
    น่า
    0.43
    Activations Density 0.000%

    No Known Activations