© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12039
    Prev
    Next
    INDEX
    Explanations

    awards and nominations

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

    This neuron detects mentions of film award names or award‐ceremony titles (e.g. “Hong Kong Film Awards”).

    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
    嫦
    -0.79
     affects
    -0.78
    当選
    -0.77
    eará
    -0.77
    updateOne
    -0.75
     кое
    -0.75
     global
    -0.74
    rase
    -0.73
    니다
    -0.72
     medically
    -0.71
    POSITIVE LOGITS
     awards
    1.26
     Awards
    1.21
     nominations
    1.15
     nominees
    1.10
    Awards
    1.09
     ceremony
    1.03
    Award
    0.99
    awards
    0.98
     AWARDS
    0.97
     ceremonies
    0.96
    Activations Density 0.050%

    No Known Activations