© 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. 131096
    Prev
    Next
    INDEX
    Explanations

    code structure, configuration

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

    machine learning hyperparameters and data handling

    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
    、
    0.49
    一定的
    0.48
     высокую
    0.46
    αιν
    0.45
    个
    0.43
     :',
    0.43
    źnie
    0.43
    úc
    0.42
     अद
    0.42
    ą
    0.42
    POSITIVE LOGITS
     myths
    0.51
     cigars
    0.51
     jsme
    0.49
     cider
    0.48
     cubes
    0.48
     dogma
    0.47
     data
    0.46
     classifier
    0.46
     chocolate
    0.46
     noodles
    0.46
    Activations Density 0.001%

    No Known Activations