© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72036
    Prev
    Next
    INDEX
    Explanations

    Greg and surnames

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

    This neuron detects occurrences of the capitalized first name “Greg.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    灩
    -3.16
    籏
    -2.66
    ⪧
    -2.66
    ⤞
    -2.56
    盦
    -2.45
     consider
    -2.45
     know
    -2.42
     schnellen
    -2.41
    rlpool
    -2.41
    anyahu
    -2.41
    POSITIVE LOGITS
    2
    4.41
    4
    3.75
    6
    3.70
    7
    3.69
    1
    3.58
    3
    3.30
    8
    3.28
    5
    3.22
    I
    3.16
    9
    3.08
    Activations Density 0.001%

    No Known Activations