© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103559
    Prev
    Next
    INDEX
    Explanations

    film director and writer

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

    The neuron is triggered by occurrences of the word “film” (as in film descriptions or listings).

    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
    sipkan
    -0.84
    員工
    -0.81
    esign
    -0.76
    RotationOrder
    -0.73
     každý
    -0.73
    nodeValue
    -0.72
    cup
    -0.72
    ([-
    -0.72
     Gór
    -0.72
     allerlei
    -0.71
    POSITIVE LOGITS
     director
    4.59
     Director
    3.63
    director
    3.53
     directors
    3.45
     writer
    3.42
    Director
    3.41
     directed
    3.16
     DIRECTOR
    2.70
    Directed
    2.70
     Directed
    2.66
    Activations Density 0.099%

    No Known Activations