© 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. 32795
    Prev
    Next
    INDEX
    Explanations

    congressional sessions and elections

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

    The neuron is picking out very high-frequency function words (common articles, prepositions, and other frequent tokens).

    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
     creadores
    -0.75
    system
    -0.71
     Celle
    -0.70
     kecuali
    -0.69
     embarazadas
    -0.68
    umna
    -0.68
     rattled
    -0.68
    创作
    -0.67
    元年
    -0.66
    参赛
    -0.66
    POSITIVE LOGITS
     session
    1.00
     Tenth
    0.97
    getahuan
    0.96
     Eleventh
    0.93
     Ninth
    0.93
     Sixth
    0.93
     Congress
    0.91
     tenth
    0.88
     Eighth
    0.88
     Seventh
    0.87
    Activations Density 0.040%

    No Known Activations