© 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. 143175
    Prev
    Next
    INDEX
    Explanations

    CAM module

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

    * **The** or **with** followed by punctuation

    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
    section
    0.50
    ข้อมูล
    0.49
    ’
    0.46
    EN
    0.46
     ยัง
    0.45
    เลือก
    0.45
    IM
    0.44
    ของ
    0.44
    info
    0.44
     ใน
    0.44
    POSITIVE LOGITS
    JlcG
    0.50
    缀
    0.50
    ница
    0.49
    צל
    0.47
    삵
    0.46
    ంట
    0.45
    зра
    0.45
    耻
    0.44
     ausge
    0.43
     Tsh
    0.43
    Activations Density 0.000%

    No Known Activations