© 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. 169381
    Prev
    Next
    INDEX
    Explanations

    language and community topics

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

    for structured lists

    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
     Đá
    0.48
     किस्मत
    0.47
     或者
    0.47
     BasicContainer
    0.47
     İn
    0.46
     మార
    0.45
     安全
    0.44
    馇
    0.44
     หา
    0.44
     Tide
    0.44
    POSITIVE LOGITS
    اة
    0.51
     ventaja
    0.48
     disponibil
    0.48
    율
    0.48
    られている
    0.47
    ого
    0.46
     localizada
    0.46
    롬
    0.46
    ياب
    0.46
    ية
    0.46
    Activations Density 0.001%

    No Known Activations