© 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. 1738
    Prev
    Next
    INDEX
    Explanations

    stopping or slowing movement

    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
    箸
    0.71
    Walk
    0.67
     велосипе
    0.65
    航空
    0.65
     Walk
    0.64
    setWalk
    0.63
     flights
    0.63
    imide
    0.63
     Fahrrad
    0.62
    泳
    0.62
    POSITIVE LOGITS
     parked
    1.57
     stopped
    1.39
     park
    1.33
     Stopped
    1.30
    park
    1.29
     slowing
    1.29
     slowed
    1.29
     deceler
    1.28
    stopped
    1.28
     halted
    1.23
    Activations Density 0.469%

    No Known Activations