© 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. 194987
    Prev
    Next
    INDEX
    Explanations

    defined specification

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

    manufacturing, audit trails, suggestive, however

    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
    ឡិចត្រូ
    0.43
    শনার
    0.41
    সম্যান
    0.40
     Mounted
    0.39
     SUCCESSFULLY
    0.39
    迌
    0.39
    িন্দা
    0.39
    সজ্জিত
    0.39
     właśnie
    0.38
     kształ
    0.38
    POSITIVE LOGITS
     ■
    0.51
    рь
    0.47
    あらゆる
    0.45
    г
    0.43
    によっては
    0.42
    記入
    0.40
    御
    0.39
     ●
    0.38
    ごとに
    0.38
    ."—
    0.38
    Activations Density 0.004%

    No Known Activations