© 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. 180540
    Prev
    Next
    INDEX
    Explanations

    unless specified, qualified buyers

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

    medical, political, total usage, and tone

    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
     חש
    0.56
     न्यू
    0.51
     אשר
    0.51
     chỉnh
    0.50
     assemblages
    0.50
     algebras
    0.50
     เพิ่ม
    0.50
     뉴
    0.49
     ลักษณะ
    0.48
     ヴィンテージ
    0.48
    POSITIVE LOGITS
    ppt
    0.50
    лаве
    0.50
    с
    0.50
    George
    0.49
    ə
    0.49
    ppb
    0.48
     <=
    0.48
    qr
    0.48
    pound
    0.47
    alex
    0.47
    Activations Density 0.000%

    No Known Activations