© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85373
    Prev
    Next
    INDEX
    Explanations

    microcirculatory bed, powder bed, fluidized bed

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

    The neuron detects the word "bed" in various contexts, particularly when related to physical beds or geographic bed references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     he
    -2.92
    ℣
    -2.88
    椟
    -2.77
    鼱
    -2.72
    愎
    -2.63
    必要がある
    -2.55
     唯美
    -2.55
    并且
    -2.53
    และ
    -2.52
    垍
    -2.52
    POSITIVE LOGITS
     staunch
    2.86
    ﮟ
    2.66
     This
    2.66
     What
    2.59
     nuanced
    2.47
     ingenious
    2.42
     Whether
    2.39
     With
    2.38
    ться
    2.38
     bolster
    2.36
    Activations Density 0.008%

    No Known Activations