© 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. 124776
    Prev
    Next
    INDEX
    Explanations

    receiving the, event opened, users may

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

    using 'ing' or 'ize'

    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
     অবকাশ
    0.51
    epub
    0.50
    ."[
    0.50
    ("@
    0.49
     begren
    0.48
    ,@
    0.48
     ഓരോ
    0.46
    čkom
    0.45
     چهار
    0.45
    isPlaying
    0.44
    POSITIVE LOGITS
    ጠቃ
    0.46
    يله
    0.45
     Acer
    0.44
    ன்ப
    0.43
     migrate
    0.42
    請求
    0.42
     perímetro
    0.42
    Rack
    0.41
    <0x9A>
    0.41
    <0xAA>
    0.41
    Activations Density 0.000%

    No Known Activations