© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9837
    Prev
    Next
    INDEX
    Explanations

    walking and related actions

    np_acts-logits-general · gemini-2.5-flash-lite

    action of walking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    🚙
    0.55
    驶
    0.53
    🚗
    0.49
     fahren
    0.48
    🏍
    0.48
    Colored
    0.47
     weaving
    0.46
    乗り
    0.45
    Insertion
    0.44
    駛
    0.44
    POSITIVE LOGITS
     Walk
    0.93
     walk
    0.87
    Walk
    0.85
     WALK
    0.85
     walks
    0.83
     walked
    0.79
     walkers
    0.78
     walkthrough
    0.77
     yür
    0.76
     Walks
    0.76
    Activations Density 0.067%

    No Known Activations