© 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. 64511
    Prev
    Next
    INDEX
    Explanations

    census or March dates

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

    The neuron is tuned to detect numeric, census‐style population and year data (as found in demographics sections).

    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
    ourne
    -0.83
    Talent
    -0.79
    辘
    -0.77
     venner
    -0.75
     frek
    -0.75
     genç
    -0.75
    ㅡ
    -0.75
     tỏ
    -0.74
    therly
    -0.74
     yüzük
    -0.74
    POSITIVE LOGITS
    ścio
    0.74
    ……。
    0.73
    tue
    0.70
    著書
    0.69
     verlieren
    0.68
    ⌨
    0.66
     situation
    0.66
    Situ
    0.66
     situations
    0.65
    )}_{
    0.65
    Activations Density 0.020%

    No Known Activations