© 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. 203262
    Prev
    Next
    INDEX
    Explanations

    options, notifications, assignments

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

    ticking away, holding court

    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
     muchos
    0.50
    าง
    0.45
    很多
    0.41
     $%
    0.41
     frame
    0.41
    Franklin
    0.41
    OFF
    0.40
     shumë
    0.40
    “
    0.40
    AX
    0.40
    POSITIVE LOGITS
     تکلیف
    0.47
    تدائي
    0.47
     уведом
    0.45
     Optionen
    0.44
     ইত্যাদি
    0.44
     आदि
    0.43
    有限公司
    0.43
    owość
    0.42
     通知
    0.42
     विकल्प
    0.42
    Activations Density 0.001%

    No Known Activations