© 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. 224308
    Prev
    Next
    INDEX
    Explanations

    building originally

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

    air comes

    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
    OGRAPHY
    0.53
    Structuring
    0.52
    $\--
    0.50
    籶
    0.49
     ме
    0.48
    𝐍
    0.47
    テーション
    0.47
     ដើម្បី
    0.47
    㜖
    0.46
    䡉
    0.46
    POSITIVE LOGITS
    o
    0.62
    r
    0.60
    rect
    0.54
    that
    0.52
    w
    0.51
    e
    0.49
    window
    0.48
    alab
    0.48
    ?
    0.48
    its
    0.48
    Activations Density 0.001%

    No Known Activations