© 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. 31800
    Prev
    Next
    INDEX
    Explanations

    names ending in ey or ley

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

    The neuron fires on tokens ending in the letters “ey” (e.g. proper names like Cockey, Barney, Janey, or code identifiers like coley).

    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
    راجع
    -0.86
     subtly
    -0.86
     improve
    -0.81
     symmetric
    -0.80
     usually
    -0.79
     facilitate
    -0.75
     simplistic
    -0.75
    門口
    -0.74
     mesure
    -0.73
     unusually
    -0.73
    POSITIVE LOGITS
    ность
    0.82
     engendered
    0.80
     тик
    0.80
    ombs
    0.79
     infor
    0.79
     București
    0.76
    DMF
    0.75
    真的是
    0.74
    чиком
    0.74
     energe
    0.74
    Activations Density 0.042%

    No Known Activations