© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32993
    Prev
    Next
    INDEX
    Explanations

    motion detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shore
    -0.71
    损
    -0.71
    handleError
    -0.71
    ourse
    -0.71
    绞
    -0.70
    汁
    -0.69
    history
    -0.69
    meliharaan
    -0.69
     окра
    -0.68
    simus
    -0.68
    POSITIVE LOGITS
     motion
    3.80
     Motion
    2.92
    motion
    2.84
    Motion
    2.81
     MOTION
    2.66
     motions
    2.44
    MOTION
    2.41
     Bewegungs
    1.95
    motions
    1.94
     PIR
    1.90
    Activations Density 0.019%

    No Known Activations