© 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. 22-GEMMASCOPE-RES-131K
    7. 71566
    Prev
    Next
    INDEX
    Explanations

    bodily discomfort or illness

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

    descriptions of physical symptoms, pain, or medical conditions in personal accounts.

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

    The neuron flags words that describe signs of malfunction or distress—whether bodily symptoms (twitches, seizures, fevers) or mechanical faults (strange noises, rough running, overheating).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     such
    -1.05
    Waiting
    -1.02
    Such
    -0.99
    나는
    -0.97
     zumindest
    -0.93
     pareti
    -0.93
    饮料
    -0.90
    such
    -0.90
     already
    -0.88
     oportunidade
    -0.88
    POSITIVE LOGITS
     refuses
    1.18
     after
    1.09
     and
    1.09
    GARET
    1.01
    égard
    0.96
     controlar
    0.96
     suspicious
    0.96
     comenz
    0.95
    ('/:
    0.95
     began
    0.94
    Activations Density 0.072%

    No Known Activations