© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83126
    Prev
    Next
    INDEX
    Explanations

    file operations or code settings

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

    The neuron activates on tokens consisting of numeric digit sequences (i.e. numbers).

    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
    FRAG
    -0.88
    Netz
    -0.76
    клар
    -0.74
    jährigen
    -0.74
     Asi
    -0.73
     Fong
    -0.71
     turismo
    -0.69
     Fountain
    -0.69
    ンプレート
    -0.69
    Instruments
    -0.68
    POSITIVE LOGITS
    旮
    0.77
     Eberhard
    0.67
    ational
    0.67
    acionales
    0.66
    彩色
    0.66
     berwarna
    0.65
     barbed
    0.65
    Servicios
    0.65
     strictly
    0.64
     Strictly
    0.64
    Activations Density 0.051%

    No Known Activations