© 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. 67177
    Prev
    Next
    INDEX
    Explanations

    limb salvage, limb bud, limb differences

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

    The neuron detects mentions of human limbs (arms, legs) and related anatomical concepts.

    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
    ⽤
    -2.59
    髡
    -2.53
    —”
    -2.34
    -“
    -2.30
    —“
    -2.28
    坭
    -2.27
    摃
    -2.27
    silien
    -2.25
    .’”
    -2.22
     многие
    -2.17
    POSITIVE LOGITS
    的
    3.14
    \
    3.06
     '
    2.98
    "
    2.75
    翆
    2.64
    时
    2.59
    á
    2.56
    他对
    2.56
    what
    2.55
    两个
    2.50
    Activations Density 0.011%

    No Known Activations