© 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. 94038
    Prev
    Next
    INDEX
    Explanations

    movie IMDb movieMovie fullMovies IMDb

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

    The neuron activates on numeric tokens (e.g. digit sequences or version/ID numbers).

    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
    錄
    -0.89
     all
    -0.87
     people
    -0.84
     recording
    -0.83
    像素
    -0.79
     recorded
    -0.76
     using
    -0.75
    嫻
    -0.75
     after
    -0.75
    百万
    -0.75
    POSITIVE LOGITS
     หนัง
    1.02
     Movie
    0.99
    Movie
    0.96
     IMDb
    0.96
     MOVIE
    0.94
    prá
    0.93
    Movies
    0.92
     IMDB
    0.91
    ítica
    0.90
    hibitor
    0.90
    Activations Density 0.010%

    No Known Activations