© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91758
    Prev
    Next
    INDEX
    Explanations

    Raymond or Ray names

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

    The neuron fires on occurrences of the name “Ray” (as in “Ray,” “Raymond,” and close variants) in the text.

    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
     ゴールド
    -0.79
    нологі
    -0.75
     several
    -0.73
     koll
    -0.72
     purpose
    -0.72
    lägg
    -0.71
     kapal
    -0.71
     Kein
    -0.71
     Given
    -0.71
     Sahne
    -0.71
    POSITIVE LOGITS
     spd
    0.82
     RAY
    0.81
    quard
    0.81
     TLV
    0.81
     insi
    0.80
     Allegretto
    0.79
    elev
    0.79
     Viper
    0.79
     NTIS
    0.78
     UNAM
    0.77
    Activations Density 0.022%

    No Known Activations