© 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. 21053
    Prev
    Next
    INDEX
    Explanations

    year associated with copyright or dates

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

    The neuron is detecting the Chinese/Japanese character “年” (used to mark “year” in dates).

    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
    ୈ
    -2.31
    渼
    -1.98
    ৢ
    -1.88
    CHRE
    -1.82
     encontraban
    -1.80
    ttää
    -1.80
    
    -1.79
    philips
    -1.79
     delito
    -1.78
    дів
    -1.77
    POSITIVE LOGITS
    h
    2.16
    p
    2.00
    in
    1.97
     have
    1.96
     -
    1.95
    that
    1.95
    OR
    1.88
    He
    1.80
    (),
    1.79
    i
    1.78
    Activations Density 0.001%

    No Known Activations