© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94219
    Prev
    Next
    INDEX
    Explanations

    Kenya, elections, census, new

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

    The neuron strongly fires on formal references to government bodies, institutional reports or surveys (often including years or statistics) and named public officials or their titles.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     vehemently
    -0.75
     pinned
    -0.75
     ślub
    -0.71
    izare
    -0.71
    ⇠
    -0.69
     summoned
    -0.69
     hauled
    -0.69
     soaked
    -0.68
     sparked
    -0.68
     noticeably
    -0.68
    POSITIVE LOGITS
    wele
    0.79
     rollout
    0.78
     revered
    0.78
    affine
    0.77
    othea
    0.73
    rony
    0.73
     Layout
    0.72
    
    0.71
     ストラップ
    0.71
    cestry
    0.71
    Activations Density 0.008%

    No Known Activations