© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21672
    Prev
    Next
    INDEX
    Explanations

    district followed by state or region

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

    The neuron fires on mentions of administrative place‐names—especially when labeling districts, towns, or similar geographic units.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    opheles
    -1.73
    に入れる
    -1.70
    をつけて
    -1.66
     bancada
    -1.64
     всѣ
    -1.62
    celotti
    -1.59
    をつける
    -1.56
    regalo
    -1.56
     Presidencia
    -1.56
    valget
    -1.55
    POSITIVE LOGITS
    at
    2.50
    3
    1.90
    section
    1.90
    ti
    1.87
    y
    1.86
    er
    1.80
    b
    1.79
    」
    1.77
    I
    1.76
     will
    1.74
    Activations Density 0.012%

    No Known Activations