© 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. 83152
    Prev
    Next
    INDEX
    Explanations

    park ranger management

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

    The neuron strongly activates on sequences of digits and numeric tokens (e.g. dates, quantities, identifiers, or any 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
     Yee
    -0.89
    rigation
    -0.79
     city
    -0.77
     городской
    -0.76
    ⓣ
    -0.74
     Parteien
    -0.72
    комнат
    -0.72
     Road
    -0.71
     کشاور
    -0.71
    ırım
    -0.71
    POSITIVE LOGITS
     rangers
    1.84
     ranger
    1.70
     Rangers
    1.49
     park
    1.41
    Rangers
    1.37
     Ranger
    1.34
     patrol
    1.34
     management
    1.26
    Management
    1.23
    Ranger
    1.23
    Activations Density 0.013%

    No Known Activations