© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20790
    Prev
    Next
    INDEX
    Explanations

    emoticons and symbols

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

    The neuron activates on inline emoji or emoticon markup (colon-delimited icon names).

    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
    -
    -2.77
    ;
    -2.48
    (
    -2.30
    ,
    -2.06
    "
    -1.92
     ensuring
    -1.84
    :
    -1.83
    .
    -1.80
    t
    -1.78
     the
    -1.77
    POSITIVE LOGITS
     něj
    2.03
     retratos
    1.98
    苼
    1.98
    
    1.90
     această
    1.84
    secuencias
    1.83
    
    1.83
    acterísticas
    1.80
     nagyon
    1.77
     москва
    1.77
    Activations Density 0.005%

    No Known Activations