© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 884
    Prev
    Next
    INDEX
    Explanations

    numbered lists of planets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    𝟮
    0.89
     ۲۰
    0.89
     ۲۰۰
    0.88
     २०२२
    0.87
    
    0.85
     ২০১০
    0.82
     ২০
    0.81
    ۰۰
    0.80
    
    0.80
     २००
    0.79
    POSITIVE LOGITS
    ​​​​
    0.67
     obliterated
    0.66
    を作
    0.62
     turban
    0.62
     suminist
    0.62
    笫
    0.61
     organize
    0.60
     creates
    0.59
     organizes
    0.59
     nonetheless
    0.58
    Activations Density 0.983%

    No Known Activations