© 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. 84076
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

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

    brief description of products

    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
    v
    0.59
    f
    0.59
    a
    0.57
    h
    0.57
    g
    0.55
    r
    0.55
    ras
    0.51
    -
    0.50
    t
    0.49
    ro
    0.47
    POSITIVE LOGITS
     иң
    0.56
     বিনিয়োগ
    0.54
    𒉆
    0.51
     কষ্ট
    0.50
     হলেন
    0.50
     তো
    0.49
     palavra
    0.49
    郆
    0.48
     luyện
    0.47
    𒅁
    0.47
    Activations Density 0.001%

    No Known Activations