© 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. 22-GEMMASCOPE-RES-131K
    4. 492
    Prev
    Next
    INDEX
    Explanations

    proper nouns or initials followed by specific tokens

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

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

    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
     chré
    -1.20
     oreja
    -1.15
    ","");
    -1.05
     potrzeby
    -1.05
    Allister
    -1.03
    原神
    -1.02
    léans
    -1.01
     cuando
    -1.00
     muñeca
    -1.00
     material
    -0.98
    POSITIVE LOGITS
    ('/:
    1.16
     ANO
    1.09
    ַּ
    1.07
    нє
    0.98
    Biblia
    0.97
    ность
    0.96
     refirió
    0.95
    место
    0.94
     Grüßen
    0.93
    焦虑
    0.93
    Activations Density 0.002%

    No Known Activations