© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    street address components

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

    This neuron detects street-address components, especially ordinal numbers (e.g., “4th,” “3rd,” “1369 Forest Ave”) in location lines.

    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
    double
    -0.93
     double
    -0.88
     doubles
    -0.85
    🅸
    -0.81
    الط
    -0.81
     dobles
    -0.79
     sinks
    -0.75
    getDouble
    -0.73
     Doppel
    -0.72
     vett
    -0.72
    POSITIVE LOGITS
    acor
    0.72
    кономі
    0.71
     trasera
    0.71
     latach
    0.70
    bė
    0.68
    ctive
    0.67
    QUENCE
    0.67
    缭
    0.66
    LETTERS
    0.65
     дъ
    0.65
    Activations Density 0.008%

    No Known Activations