© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68675
    Prev
    Next
    INDEX
    Explanations

    what is obtained

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

    The neuron activates on numeric tokens, i.e. any numbers or quantities appearing in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ’
    -1.96
    ”,
    -1.77
        
    -1.77
    All
    -1.74
                
    -1.70
    9
    -1.70
    most
    -1.67
    </sup>
    -1.66
    

    -1.63
    ).”
    -1.62
    POSITIVE LOGITS
     to
    1.83
     แต่
    1.72
    
    1.59
     insanlar
    1.59
    Dette
    1.56
    ݮ
    1.55
    somewhat
    1.54
     גם
    1.51
     mortes
    1.51
    了一個
    1.50
    Activations Density 0.028%

    No Known Activations