© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83831
    Prev
    Next
    INDEX
    Explanations

    resting places and anatomical beds

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

    The neuron identifies and activates for references to beds in various contexts such as hospital beds, nursing home beds, and bedroom furniture.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    u
    -3.36
     was
    -3.02
    儅
    -2.69
    茑
    -2.64
    y
    -2.61
    an
    -2.61
    âce
    -2.59
    軚
    -2.58
    ا
    -2.52
    a
    -2.50
    POSITIVE LOGITS
     
    3.03
    -
    3.00
    When
    2.88
    Initially
    2.88
    There
    2.78
    Each
    2.78
    Both
    2.77
    </strong>
    2.73
    Ultimately
    2.72
    If
    2.63
    Activations Density 0.001%

    No Known Activations