© 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. 62605
    Prev
    Next
    INDEX
    Explanations

    specific topics

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

    purpose and function

    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
     quod
    0.50
    "
    0.48
    '
    0.47
    -
    0.45
    *
    0.44
     tracts
    0.44
    Claudia
    0.44
    {
    0.43
     enthr
    0.43
     therapeutic
    0.42
    POSITIVE LOGITS
     ऑर्
    0.50
     डिलीवरी
    0.48
     అలా
    0.48
    椇
    0.48
     Obstetrics
    0.47
     بونس
    0.46
    汕
    0.46
    憉
    0.46
    ियस
    0.46
     बिल्डिंग
    0.46
    Activations Density 0.000%

    No Known Activations