© 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. 22-GEMMASCOPE-RES-131K
    7. 39171
    Prev
    Next
    INDEX
    Explanations

    first names followed by last names

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

    The neuron primarily activates on personal names (proper nouns referring to individuals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     for
    -1.42
    tokenId
    -1.34
     would
    -1.27
     vêtement
    -1.23
     especially
    -1.23
     even
    -1.20
     since
    -1.19
     regioni
    -1.16
     as
    -1.16
     lupo
    -1.12
    POSITIVE LOGITS
     alleged
    1.48
     徒歩
    1.33
    レム
    1.32
    ಆ
    1.32
    说实话
    1.32
    ֲ
    1.32
    bbing
    1.31
    有两个
    1.31
     descrito
    1.30
     claramente
    1.30
    Activations Density 0.079%

    No Known Activations