© 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. 86762
    Prev
    Next
    INDEX
    Explanations

    physics and states of being

    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
     width
    -0.74
    Taurus
    -0.73
     długość
    -0.72
     पहुंच
    -0.71
    >
    -0.70
    uari
    -0.70
     tils
    -0.68
    arino
    -0.68
    eded
    -0.68
     scalar
    -0.67
    POSITIVE LOGITS
     rag
    1.13
     sleeping
    1.04
     asleep
    1.01
     Rigidbody
    0.92
    Rigidbody
    0.91
     dormir
    0.91
    Sleeping
    0.90
     velocity
    0.87
     Rag
    0.85
     constraints
    0.82
    Activations Density 0.007%

    No Known Activations