© 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. 25522
    Prev
    Next
    INDEX
    Explanations

    when or before

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

    during or when

    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
    ™.
    0.51
    。
    0.49
    !.
    0.48
     그래서
    0.46
    ទេ។
    0.43
    ～。
    0.41
     ያሉ
    0.40
     ہیں۔
    0.40
    ®.
    0.40
    のではなく
    0.39
    POSITIVE LOGITS
     during
    0.92
    during
    0.75
     durante
    0.75
     протягом
    0.71
     během
    0.66
     tijdens
    0.65
     خلال
    0.63
     DURING
    0.63
     durant
    0.62
     when
    0.61
    Activations Density 0.306%

    No Known Activations