© 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. 34-GEMMASCOPE-RES-131K
    7. 106245
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

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

    The neuron is activated by long multi-digit numeric sequences (e.g. reference or accession numbers).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    าก็
    -1.00
    உ
    -0.99
     Reli
    -0.94
    +:+
    -0.94
     カジュアル
    -0.94
     обществе
    -0.93
     here
    -0.93
    ILITY
    -0.92
     Ucraina
    -0.91
    车上
    -0.91
    POSITIVE LOGITS
     it
    1.20
    ),
    1.04
              
    1.03
    ∼
    0.95
    廼
    0.95
     to
    0.93
     wraz
    0.91
     frühen
    0.90
                
    0.88
    },
    0.88
    Activations Density 0.007%

    No Known Activations