© 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. 38459
    Prev
    Next
    INDEX
    Explanations

    erste, obere

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

    process, block, filter, exchange

    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
    ایات
    0.45
     translational
    0.45
    V
    0.44
     derived
    0.44
     precursor
    0.43
    گیری
    0.43
    derived
    0.41
     punches
    0.41
     emails
    0.41
     librarian
    0.41
    POSITIVE LOGITS
     Стра
    0.56
    erste
    0.52
     Та
    0.52
     woning
    0.49
     oben
    0.48
    𝖚
    0.48
     Функ
    0.47
     Ги
    0.47
     oberen
    0.47
     ersten
    0.47
    Activations Density 0.000%

    No Known Activations