© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34506
    Prev
    Next
    INDEX
    Explanations

    surgical limb removal

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

    medical content related to amputations and limb-related medical conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects the “amp” subword—i.e. tokens related to amputation or amputations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    head
    -0.91
    oucí
    -0.79
    それだけ
    -0.73
     Headache
    -0.70
     VIOL
    -0.70
    uty
    -0.70
     FILLER
    -0.70
    肋
    -0.70
    ęty
    -0.70
    roids
    -0.69
    POSITIVE LOGITS
     amputation
    2.42
     limb
    1.97
     amput
    1.88
     limbs
    1.65
     Limb
    1.55
     amp
    1.45
    limb
    1.42
     prosthetic
    1.38
     stumps
    1.27
     leg
    1.16
    Activations Density 0.077%

    No Known Activations