© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1716
    Prev
    Next
    INDEX
    Explanations

    knotted things

    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
    Stamp
    0.73
    
    0.73
    ᶜ
    0.72
     Crater
    0.71
    ادیه
    0.71
    铣
    0.71
     crater
    0.71
    銑
    0.70
     Milling
    0.68
     regno
    0.68
    POSITIVE LOGITS
     rope
    2.46
     ropes
    2.39
     knotted
    2.33
     Rope
    2.33
     tying
    2.27
     knots
    2.23
     knot
    2.19
     cords
    2.16
     twine
    2.13
     tied
    2.11
    Activations Density 1.207%

    No Known Activations