© 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. 64934
    Prev
    Next
    INDEX
    Explanations

    change color, theme, or language

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

    The neuron primarily detects numeric tokens—digits, numbers, and numeric constants—wherever they appear.

    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
    rowData
    -0.99
     intersper
    -0.93
    Klub
    -0.88
    fillRect
    -0.85
    Etimo
    -0.84
    boBox
    -0.83
    chule
    -0.81
    amaan
    -0.81
    Historia
    -0.80
     caravans
    -0.80
    POSITIVE LOGITS
     language
    2.13
    language
    1.66
     color
    1.44
     languages
    1.39
     Language
    1.39
     preferred
    1.39
     theme
    1.38
    Language
    1.30
     sound
    1.28
     prefer
    1.24
    Activations Density 0.062%

    No Known Activations