© 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. 83642
    Prev
    Next
    INDEX
    Explanations

    Indian states and Bally places

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

    The neuron activates on standalone numeric tokens (i.e. 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     της
    -2.64
    ڧ
    -2.63
    และ
    -2.59
    oplasmic
    -2.56
     ausein
    -2.50
    
    -2.48
    糴
    -2.48
     сделали
    -2.39
    ”，
    -2.38
     丁目
    -2.36
    POSITIVE LOGITS
     BOTH
    2.64
     AFTER
    2.64
     Keine
    2.56
     
    2.50
     Various
    2.41
     Other
    2.38
     Either
    2.36
    ⟝
    2.34
    少ない
    2.33
     OTHER
    2.31
    Activations Density 0.004%

    No Known Activations