© 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. 34-GEMMASCOPE-RES-131K
    7. 64373
    Prev
    Next
    INDEX
    Explanations

    reunion, Class, Attorney, Judge

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

    The neuron consistently fires on numerical tokens or numeric sequences (years, ages, page or case numbers, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Spotted
    -0.79
    亏
    -0.79
    tslib
    -0.75
    Upstairs
    -0.74
    
    -0.73
    ందు
    -0.72
     живут
    -0.72
     Spanien
    -0.72
     sacar
    -0.71
     soutě
    -0.69
    POSITIVE LOGITS
     détaillés
    0.76
    ละเอียด
    0.75
    Dias
    0.73
    urion
    0.70
     inoltre
    0.70
    cus
    0.68
     PDA
    0.68
    carbox
    0.68
    gné
    0.68
    dias
    0.68
    Activations Density 0.011%

    No Known Activations