© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9620
    Prev
    Next
    INDEX
    Explanations

    prior experience level

    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
    
    1.65
     임
    1.55
     성
    1.50
    
    1.47
     โดย
    1.46
     دی
    1.45
    
    1.43
    牞
    1.38
     เจ้า
    1.38
     นอกจาก
    1.37
    POSITIVE LOGITS
    ifiant
    1.18
    ällen
    1.16
    atively
    1.13
    íf
    1.09
    barer
    1.08
    attamente
    1.08
    -,
    1.04
    abler
    1.03
    context
    1.03
    ativen
    1.02
    Activations Density 0.772%

    No Known Activations