© 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. 47930
    Prev
    Next
    INDEX
    Explanations

    genres and media types

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

    The neuron activates on single words naming a work’s genre or subgenre (e.g. thriller, comedy, coming-of-age, buddy, creature).

    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
    vertebrate
    -1.23
    quirer
    -1.18
     verfügbar
    -1.17
    瞓
    -1.16
    rofl
    -1.16
    ==='
    -1.15
    aughter
    -1.13
     popolari
    -1.12
     verschiedener
    -1.11
     przód
    -1.11
    POSITIVE LOGITS
    Spesifikasi
    1.20
     almas
    1.20
     masaj
    1.20
    orenje
    1.20
     Then
    1.19
     colombiana
    1.16
     Possibly
    1.13
     another
    1.13
    Martes
    1.13
     maybe
    1.11
    Activations Density 0.128%

    No Known Activations