© 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. 77614
    Prev
    Next
    INDEX
    Explanations

    technical terms and designs

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

    The neuron is selectively activating on numeric values and coordinate‐style tokens (e.g. dimensions, parentheses with numbers), i.e. it detects technical numeric/specification data.

    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
     Starbucks
    -0.83
     Xbox
    -0.75
     Vancouver
    -0.75
     iPod
    -0.74
     IOS
    -0.74
    厦
    -0.71
     inşa
    -0.71
    кисло
    -0.71
     Hawaiian
    -0.70
     calendario
    -0.70
    POSITIVE LOGITS
    Pads
    0.89
     kic
    0.88
     документа
    0.88
    cyjny
    0.85
     кише
    0.85
     libur
    0.83
    Schematic
    0.81
    舛
    0.81
     schematic
    0.79
     syd
    0.78
    Activations Density 0.019%

    No Known Activations