© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    date formats MM/DD/YYYY or DD/MM/YYYY

    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
    жуть
    0.48
    ዟ
    0.47
    نیٹ
    0.43
     але
    0.43
     आश्च
    0.41
    놁
    0.41
    blusa
    0.40
    ጥረ
    0.39
    TreeNavigator
    0.39
     damning
    0.38
    POSITIVE LOGITS
    /
    0.58
    ↵
    0.52
    u
    0.49
     for
    0.48
    R
    0.48
     ot
    0.47
    +
    0.47
     pts
    0.46
    in
    0.46
    ROP
    0.45
    Activations Density 0.043%

    No Known Activations