© 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. 34-GEMMASCOPE-RES-131K
    7. 93040
    Prev
    Next
    INDEX
    Explanations

    dys- prefixes for disorders

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

    medical prefixes like "dys-" that indicate abnormal or impaired functioning in medical terms.

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

    The neuron detects words beginning with the prefix “dys-,” i.e. terms indicating disorders or abnormal conditions.

    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
    izace
    -0.76
    voyage
    -0.75
    INNOV
    -0.74
     otras
    -0.73
    誘惑
    -0.73
    と思い
    -0.71
     sogar
    -0.71
    valla
    -0.70
     innovations
    -0.69
    imagination
    -0.69
    POSITIVE LOGITS
     dys
    1.28
     Dys
    1.21
    dys
    1.06
    FUNCTION
    1.03
    Dys
    0.96
    functions
    0.88
    junction
    0.87
    い
    0.84
    Analysts
    0.82
    Czy
    0.81
    Activations Density 0.032%

    No Known Activations