© 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. 86798
    Prev
    Next
    INDEX
    Explanations

    screen, batch, gallery

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

    code structure snippets

    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
    の
    0.54
    क
    0.53
    ב
    0.53
    パリ
    0.51
    コー
    0.51
    ः
    0.51
    हरू
    0.50
    נ
    0.50
    競争
    0.49
    アー
    0.49
    POSITIVE LOGITS
     sparkly
    0.46
     alem
    0.43
     prequel
    0.41
     Composer
    0.40
     cropped
    0.40
     screen
    0.39
     chrome
    0.39
     बैच
    0.39
     batch
    0.39
     gallery
    0.39
    Activations Density 0.000%

    No Known Activations