© 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. 10-GEMMASCOPE-RES-131K
    7. 110944
    Prev
    Next
    INDEX
    Explanations

    film

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

    The neuron primarily detects mentions of the word “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_10/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
     become
    -2.59
    
    -2.36
    ’
    -2.31
    🛖
    -2.23
    咝
    -2.22
    也不能
    -2.17
    馀
    -2.14
    分明
    -2.08
     effet
    -2.08
     Other
    -2.08
    POSITIVE LOGITS
     此
    2.92
    </strong>
    2.89
    猻
    2.88
    </h3>
    2.56
    derdag
    2.48
    菹
    2.47
    </i>
    2.45
    汌
    2.39
    u
    2.39
    ágenes
    2.38
    Activations Density 0.024%

    No Known Activations