© 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. 212348
    Prev
    Next
    INDEX
    Explanations

    construction specifications

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

    programming and technical contexts

    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
     outperformed
    0.50
     chromospheric
    0.49
     concomitant
    0.47
     vented
    0.46
     nausea
    0.44
    )[[
    0.44
     ventricular
    0.43
     Chakraborty
    0.43
     announced
    0.43
     halo
    0.42
    POSITIVE LOGITS
    <
    0.48
     árboles
    0.47
    树
    0.46
    Creators
    0.45
    钱包
    0.45
    菽
    0.45
    欧洲
    0.44
    ર્
    0.43
    视图
    0.43
    罗
    0.43
    Activations Density 0.000%

    No Known Activations