© 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. 10-GEMMASCOPE-RES-131K
    7. 60382
    Prev
    Next
    INDEX
    Explanations

    Perry

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

    The neuron responds specifically to occurrences of the proper name “Perry.”

    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
    肫
    -2.78
    玙
    -2.73
    pulseira
    -2.52
    ⟝
    -2.45
    諼
    -2.44
    jaqueta
    -2.42
    扞
    -2.42
    蛩
    -2.34
    廕
    -2.34
    es
    -2.34
    POSITIVE LOGITS
    ization
    3.16
    ｺ
    2.88
    Most
    2.48
    ～　
    2.44
    All
    2.33
    ﾍ
    2.30
    Not
    2.20
    得太
    2.16
     камня
    2.14
    不时
    2.14
    Activations Density 0.004%

    No Known Activations