© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8615
    Prev
    Next
    INDEX
    Explanations

    ถาม/แนะนำ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     Kullan
    0.91
     reis
    0.89
     Zhao
    0.88
     kumar
    0.87
     *.
    0.86
     日
    0.85
     lider
    0.83
     赤
    0.83
     rahat
    0.82
     代
    0.81
    POSITIVE LOGITS
    สอง
    1.52
    แล้ว
    1.48
    เพียง
    1.47
    จ
    1.43
    มา
    1.41
    แม
    1.40
    ๆ
    1.39
    ส
    1.37
    ไป
    1.35
    อีก
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.