© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40175
    Prev
    Next
    INDEX
    Explanations

    names followed by possessive 's

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

    The neuron detects author or contributor names (proper personal names) in bibliographic or byline sections.

    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
     both
    -1.98
     even
    -1.38
     granada
    -1.36
     countless
    -1.36
     sowohl
    -1.33
     CHECKBOX
    -1.30
     poliester
    -1.27
     birra
    -1.27
    年生
    -1.26
     dozens
    -1.23
    POSITIVE LOGITS
     who
    1.63
    妡
    1.35
     červen
    1.29
    栳
    1.22
     

    1.21
     допомогою
    1.20
    毉
    1.20
    </i>
    1.17
     rocas
    1.16
     červ
    1.16
    Activations Density 0.011%

    No Known Activations