© 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. 220705
    Prev
    Next
    INDEX
    Explanations

    accomplishments andsurvive insum uptitles ()contacts brightFireworks display

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

    getting started

    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
    ت
    0.52
    肘
    0.50
     કેવી
    0.49
     muốn
    0.48
    م
    0.47
    щите
    0.46
    环境变量
    0.46
    colormap
    0.46
    口腔
    0.45
    さに
    0.45
    POSITIVE LOGITS
     bol
    0.49
    č
    0.47
    isphere
    0.45
    urilor
    0.45
     Mug
    0.45
    uzione
    0.44
     delhi
    0.44
     lei
    0.43
    unción
    0.43
    Gosudarstvennyj
    0.43
    Activations Density 0.000%

    No Known Activations