© 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. 23625
    Prev
    Next
    INDEX
    Explanations

    movement and coordination

    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
    odule
    -0.78
    argv
    -0.77
    ða
    -0.73
    Missouri
    -0.69
     Ferr
    -0.69
    ⌊
    -0.69
    ;=
    -0.69
    )](
    -0.68
     reprend
    -0.68
    🗳
    -0.68
    POSITIVE LOGITS
     coordination
    3.59
     Coordination
    2.91
     coordinated
    2.86
    Coordination
    2.61
     coordin
    2.56
     coordinación
    2.50
     coordinate
    2.48
     координа
    2.47
     coord
    2.42
     coordinating
    2.30
    Activations Density 0.028%

    No Known Activations