© 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. 10-GEMMASCOPE-RES-131K
    4. 10259
    Prev
    Next
    INDEX
    Explanations

    movies and titles

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

    The neuron is looking for named titles or proper‐name references (e.g. movie, book, song, or character names).

    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
     hierzu
    -1.37
    While
    -1.17
     into
    -1.14
    佺
    -1.13
     hierfür
    -1.13
    פן
    -1.13
     unabhängig
    -1.11
    flox
    -1.11
    της
    -1.10
     улыба
    -1.10
    POSITIVE LOGITS
     films
    1.27
     movie
    1.27
     documents
    1.13
     film
    1.11
     so
    1.09
     женский
    1.09
     women
    1.03
     filme
    1.01
     Won
    1.01
     motif
    1.01
    Activations Density 0.043%

    No Known Activations