© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104282
    Prev
    Next
    INDEX
    Explanations

    Political classifications and specific identifiers

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

    The neuron fires on numeric tokens or numeric expressions (i.e. digits, decimals, counts).

    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
    
    -1.97
     Sehingga
    -1.76
    襴
    -1.72
    Kedves
    -1.70
    PAIGN
    -1.70
    Lycka
    -1.70
    茈
    -1.67
    苙
    -1.66
    を注文
    -1.65
    橚
    -1.65
    POSITIVE LOGITS
    ↵
    1.97
    ’
    1.70
    </strong>
    1.66
      
    1.65
    虽然
    1.61
     also
    1.59
    );
    1.53
    ？！”
    1.50
     –
    1.49
     has
    1.48
    Activations Density 0.000%

    No Known Activations