© 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. 104599
    Prev
    Next
    INDEX
    Explanations

    anti-tracking or coverage

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

    春秋时期

    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
    :
    0.50
    *
    0.50
     bore
    0.48
    a
    0.48
     frequentemente
    0.47
    ;
    0.46
     esclare
    0.46
    *)
    0.45
     kerap
    0.45
    霹
    0.45
    POSITIVE LOGITS
     البيانات
    0.46
     স্যাম
    0.45
    琏
    0.44
     ሞ
    0.44
     सैम
    0.43
    يت
    0.42
     الجرس
    0.41
    亚
    0.41
     selfishness
    0.41
    缁
    0.41
    Activations Density 0.000%

    No Known Activations