© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95598
    Prev
    Next
    INDEX
    Explanations

    correction to paper

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

    The neuron activates on numeric tokens—any standalone numbers or digit‐containing expressions in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     BASIN
    -0.95
     helpen
    -0.94
     trouve
    -0.90
    就好
    -0.88
    unjungi
    -0.86
     poden
    -0.85
     solution
    -0.85
     atlet
    -0.84
     juſt
    -0.84
    防疫
    -0.84
    POSITIVE LOGITS
    outWeight
    0.99
    우
    0.95
     encargado
    0.94
    Ꮲ
    0.93
    ÊNCIAS
    0.93
    DOI
    0.93
     OGSÅ
    0.92
    Carriera
    0.92
    金币
    0.89
    AB
    0.88
    Activations Density 0.008%

    No Known Activations