© 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. 55908
    Prev
    Next
    INDEX
    Explanations

    Birmingham, Alabama

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

    The neuron detects numeric tokens (especially volume, page, and year numbers) in legal citation strings.

    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
    Trig
    -0.85
     авиа
    -0.83
    ürlich
    -0.80
    🐊
    -0.80
     bied
    -0.79
    isław
    -0.77
    ㎡
    -0.77
    DPS
    -0.75
    inev
    -0.75
     AVI
    -0.75
    POSITIVE LOGITS
     Birmingham
    2.08
    Birmingham
    1.97
     Alabama
    1.58
    Alabama
    1.38
     UAB
    1.30
    BIR
    1.05
     Bama
    0.85
    irmingham
    0.84
     Truss
    0.83
     Vulcan
    0.82
    Activations Density 0.049%

    No Known Activations