© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42614
    Prev
    Next
    INDEX
    Explanations

    Noel or Kaye names

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

    The neuron activates on capitalized named‐entity tokens (people’s names, place names, and other proper nouns).

    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
    i
    -3.17
    U
    -3.14
    x
    -3.14
    v
    -2.89
    過程
    -2.75
    ции
    -2.75
    งาน
    -2.70
    橚
    -2.64
    B
    -2.63
    }$
    -2.50
    POSITIVE LOGITS
    pecabe
    2.95
    brinco
    2.81
    鴣
    2.63
    pulseira
    2.58
    </i>
    2.42
    躂
    2.38
    sandalia
    2.38
    zmm
    2.33
    colgante
    2.27
    "",
    2.25
    Activations Density 0.048%

    No Known Activations