© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58297
    Prev
    Next
    INDEX
    Explanations

    Mao Zedong

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

    The neuron fires strongly on digit‐only tokens (especially multi‐digit numbers such as years or other numeric identifiers).

    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
    rawy
    -0.84
     ซ
    -0.75
    cially
    -0.75
    GeneratedCode
    -0.74
     הב
    -0.74
    étoit
    -0.73
     الشب
    -0.73
    膻
    -0.72
    󠁴
    -0.72
    메
    -0.71
    POSITIVE LOGITS
     Cultural
    1.47
     Mao
    1.44
    Cultural
    1.33
     Chairman
    1.22
    Mao
    1.16
    Chairman
    1.09
    文化
    1.06
     chairman
    0.95
     CULTURAL
    0.90
     文化
    0.89
    Activations Density 0.024%

    No Known Activations