© 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. 66024
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

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

    The neuron consistently fires on multi‐digit numeric tokens (e.g. long numbers, years, or measurement values).

    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
    llium
    -0.81
     pleased
    -0.75
    genza
    -0.73
     Still
    -0.72
     स्थिति
    -0.71
     अभी
    -0.71
     учета
    -0.70
    Ѓ
    -0.70
     tahun
    -0.70
     kesan
    -0.69
    POSITIVE LOGITS
    tivamente
    0.83
    𝐙
    0.81
    ☾
    0.81
    讨论
    0.80
    sidian
    0.79
     Getter
    0.78
     dehors
    0.78
    🤏
    0.78
     pueblo
    0.77
    Ruj
    0.76
    Activations Density 0.000%

    No Known Activations