© 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. 69876
    Prev
    Next
    INDEX
    Explanations

    feature film or length

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

    The neuron detects mentions of film awards and their category names, especially phrases like “Outstanding Directing in a Feature Film.”

    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
     gogh
    -0.77
    出版社
    -0.74
    Chord
    -0.71
    htb
    -0.71
    Bộ
    -0.70
     %#
    -0.70
     utensi
    -0.69
    òi
    -0.68
    věd
    -0.68
     =>{
    -0.67
    POSITIVE LOGITS
     feature
    4.78
    feature
    3.92
     Feature
    3.83
    Feature
    3.67
     features
    3.30
     FEATURE
    3.06
    FEATURE
    2.80
     Features
    2.70
    features
    2.59
    Features
    2.42
    Activations Density 0.045%

    No Known Activations