© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12629
    Prev
    Next
    INDEX
    Explanations

    diverse teams and imagery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ‍
    1.84
    ts
    1.72
    textAppearance
    1.71
    sh
    1.67
    ‌
    1.65
    
    1.61
    n
    1.60
    sp
    1.57
    sw
    1.55
    ⁣
    1.54
    POSITIVE LOGITS
    הר
    1.98
     Sejam
    1.96
     调用
    1.95
     lɛ
    1.94
     רבי
    1.91
    تمر
    1.91
    ה
    1.90
     Laat
    1.90
    кансер
    1.90
    ลม
    1.89
    Activations Density 0.123%

    No Known Activations