© 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. 127645
    Prev
    Next
    INDEX
    Explanations

    swine fever, WoW Tailoring

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

    The neuron responds to named entities and proper nouns (e.g., place names, disease names, character or product titles).

    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
    .’
    -3.17
    ’,
    -3.16
    )’
    -3.13
    ’)
    -3.11
    ’.
    -3.06
    ).
    -3.00
    ’-
    -2.86
    ”،
    -2.78
    ?’
    -2.75
    ,’
    -2.72
    POSITIVE LOGITS
     在
    3.27
    謌
    3.13
     也
    3.09
    釹
    2.98
     但
    2.97
    蹰
    2.72
     '
    2.52
     efficacité
    2.50
    躋
    2.50
    และ
    2.47
    Activations Density 0.008%

    No Known Activations