© 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. 3944
    Prev
    Next
    INDEX
    Explanations

    competitive deals

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

    foreign language suffixes

    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
     عشر
    0.37
     並
    0.35
    ift
    0.35
    ichter
    0.35
     wobei
    0.35
     المجلس
    0.34
     ক্রী
    0.34
     सिटी
    0.33
    差異
    0.33
     కలి
    0.33
    POSITIVE LOGITS
    u
    0.46
    Durante
    0.43
    스는
    0.40
    s
    0.40
    sthe
    0.38
    :
    0.38
    D
    0.38
    Sebelum
    0.38
    스가
    0.37
    Hướng
    0.36
    Activations Density 0.160%

    No Known Activations