© 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. 22-GEMMASCOPE-RES-131K
    7. 36591
    Prev
    Next
    INDEX
    Explanations

    San Francisco

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

    The neuron fires on numeric tokens (digits or numbers) wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     whiteColor
    -0.94
     altså
    -0.93
     misalnya
    -0.91
     Biophys
    -0.91
     acol
    -0.89
     Initially
    -0.88
     Though
    -0.87
     Usually
    -0.86
     Although
    -0.85
    tvr
    -0.85
    POSITIVE LOGITS
    ということです
    0.89
    karte
    0.81
    取って
    0.80
    specifically
    0.80
    ローブ
    0.79
    veless
    0.75
     blom
    0.75
    𓆏
    0.74
     سيارة
    0.74
    鹇
    0.73
    Activations Density 0.054%

    No Known Activations