© 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. 191950
    Prev
    Next
    INDEX
    Explanations

    browsing archives or features

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

    really good

    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
     practice
    0.46
    毎週
    0.43
     visit
    0.42
     [
    0.41
    AS
    0.41
    assertInstanceOf
    0.39
     hors
    0.39
    Sunday
    0.39
    必要
    0.38
    SqlServer
    0.37
    POSITIVE LOGITS
    𝙣
    0.50
     ángulo
    0.48
     undulating
    0.47
    ோட
    0.46
     సంస్థ
    0.46
    वारीत
    0.46
     ângulo
    0.46
    𝑳
    0.46
    𝘾
    0.46
     Pattes
    0.45
    Activations Density 0.000%

    No Known Activations