© 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. 103270
    Prev
    Next
    INDEX
    Explanations

    constructorhtml

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

    The neuron is detecting tokens that contain or consist of numeric values (digits or 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
     PyTuple
    -0.92
    melis
    -0.90
    mband
    -0.86
    clé
    -0.81
    赈
    -0.79
     AttributeSet
    -0.77
    圣节
    -0.76
     ActionListener
    -0.76
    وزی
    -0.75
    🔋
    -0.75
    POSITIVE LOGITS
    bilt
    0.81
     lại
    0.81
     erz
    0.81
    潸
    0.79
    Hersteller
    0.79
    を選び
    0.78
    第三
    0.77
     enum
    0.75
     adjustable
    0.74
    अप
    0.73
    Activations Density 0.001%

    No Known Activations