© 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. 103792
    Prev
    Next
    INDEX
    Explanations

    running and walking

    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
    Ώ
    -0.79
    ocyan
    -0.77
    angler
    -0.77
    ライダー
    -0.72
    uchy
    -0.71
     fevereiro
    -0.71
     оформ
    -0.69
     сма
    -0.69
    UTC
    -0.68
    axel
    -0.68
    POSITIVE LOGITS
     running
    3.94
     run
    3.19
    running
    3.16
    Running
    3.06
     Running
    2.95
     walking
    2.52
     Run
    2.50
    RUNNING
    2.48
     runs
    2.48
     RUN
    2.47
    Activations Density 0.040%

    No Known Activations