© 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. 86976
    Prev
    Next
    INDEX
    Explanations

    movie genres

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

    The main thing this neuron does is spot genre labels and tone/style descriptors (e.g. suspense, horror, comedy, drama, romance, action, etc.).

    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
     on
    -1.69
     who
    -1.44
     use
    -1.39
    倹
    -1.35
     utilizan
    -1.34
     your
    -1.31
     worden
    -1.30
    着一个
    -1.27
     mencion
    -1.23
     for
    -1.22
    POSITIVE LOGITS
    still
    1.41
     registre
    1.31
     liev
    1.30
     еще
    1.24
     still
    1.24
     orale
    1.23
     espagnol
    1.22
     vitale
    1.20
     hunne
    1.20
     ещё
    1.19
    Activations Density 0.042%

    No Known Activations