© 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. 102686
    Prev
    Next
    INDEX
    Explanations

    Google Analytics tracking IDs

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

    This neuron primarily detects numeric tokens (digits, version numbers, IDs) in code or markup.

    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
    werfen
    -0.74
     Dank
    -0.74
    dsky
    -0.73
     participante
    -0.72
     critica
    -0.72
     BUR
    -0.72
     कंप
    -0.69
    Ẩ
    -0.69
     marry
    -0.69
    glor
    -0.68
    POSITIVE LOGITS
     UA
    1.07
    UA
    0.91
     GA
    0.90
     urchin
    0.85
    Tracker
    0.82
    anonym
    0.81
     georgia
    0.80
     TEA
    0.79
     Georgia
    0.79
    oogle
    0.78
    Activations Density 0.020%

    No Known Activations