© 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. 102083
    Prev
    Next
    INDEX
    Explanations

    common themes or purpose

    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
     us
    0.55
     ayahuasca
    0.51
     trang
    0.50
     piz
    0.49
     minuta
    0.48
     giờ
    0.48
    نیم
    0.47
    ン
    0.47
     Bo
    0.47
     Бо
    0.47
    POSITIVE LOGITS
    স্বামী
    0.48
    ндагы
    0.48
    শের
    0.47
    Strategic
    0.46
    麿
    0.46
    針對
    0.45
    মবার
    0.45
    的角度
    0.45
    的時間
    0.45
    人
    0.45
    Activations Density 0.000%

    No Known Activations