© 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. 116210
    Prev
    Next
    INDEX
    Explanations

    noun or adjective followed by verb

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

    identifying key elements or characteristics

    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
     Và
    0.52
    ҳо
    0.49
    淌
    0.47
    ayu
    0.47
    ায়ন
    0.46
    𝚎
    0.46
    ırı
    0.46
     cải
    0.45
    ﯿ
    0.44
     Ayu
    0.44
    POSITIVE LOGITS
    n
    0.64
     edges
    0.55
    quiz
    0.54
     boundedness
    0.54
    kyl
    0.51
    ن
    0.50
    st
    0.49
    todolist
    0.49
    nem
    0.48
    leden
    0.47
    Activations Density 0.003%

    No Known Activations