© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110644
    Prev
    Next
    INDEX
    Explanations

    physical grabbing actions

    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
    つなが
    -0.95
     bought
    -0.94
     in
    -0.93
    强大
    -0.92
    櫥
    -0.91
     Präsentation
    -0.90
    过多
    -0.90
    仕掛け
    -0.90
     Bought
    -0.90
     tapped
    -0.90
    POSITIVE LOGITS
     Grab
    2.05
     grabs
    1.98
     grab
    1.98
    grab
    1.96
    Grab
    1.80
     hold
    1.59
     grabbed
    1.59
     grabbing
    1.43
    hold
    1.27
     handful
    1.27
    Activations Density 0.010%

    No Known Activations