© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45302
    Prev
    Next
    INDEX
    Explanations

    institution, award, or title followed by "of" or "for"

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

    This neuron detects tokens that are part of proper names of organizations, institutions, awards, or formal entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    pierw
    -0.91
    کیف
    -0.88
    際に
    -0.87
     povezave
    -0.86
     olvidado
    -0.85
    ündete
    -0.85
     eingeladen
    -0.85
    قامت
    -0.84
     impresiones
    -0.84
    يست
    -0.84
    POSITIVE LOGITS
    參考文獻
    0.94
     überhaupt
    0.88
    參考資料
    0.87
     tán
    0.87
     aldea
    0.86
    windig
    0.85
    <bos>
    0.85
     palme
    0.84
     adolescente
    0.83
    Iglesia
    0.83
    Activations Density 0.255%

    No Known Activations