© 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. 9496
    Prev
    Next
    INDEX
    Explanations

    force and related physics terms

    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
     पत्
    0.98
     확장
    0.94
    덱
    0.90
     сочета
    0.89
    높
    0.89
    kses
    0.86
     notches
    0.85
    segmented
    0.83
    툭
    0.82
    btree
    0.82
    POSITIVE LOGITS
     thermodynamics
    1.33
     Thermodynamics
    1.30
    运动
    1.21
     Joule
    1.16
     electrochemical
    1.16
    Electro
    1.15
     physics
    1.13
     Einstein
    1.13
    荷
    1.12
     Helmholtz
    1.11
    Activations Density 0.060%

    No Known Activations