© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 87949
    Prev
    Next
    INDEX
    Explanations

    place names and locations

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

    pipeline architecture

    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
     Phòng
    0.53
     よく
    0.52
     মোবাইল
    0.49
     말미암아
    0.49
    $/../../
    0.48
     Kochubei
    0.47
     punishable
    0.46
     Jacobsen
    0.46
     ಹೊರ
    0.46
    ,*/}
    0.46
    POSITIVE LOGITS
    '
    0.49
    فته
    0.49
     posts
    0.47
     revolutions
    0.47
    יה
    0.46
    ं
    0.46
     auditor
    0.46
     elemento
    0.46
     opl
    0.46
    ैर्य
    0.46
    Activations Density 0.000%

    No Known Activations