© 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. 60450
    Prev
    Next
    INDEX
    Explanations

    romance, mystery, genre descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     FICTION
    -1.02
    edores
    -0.94
    ltr
    -0.94
    ysł
    -0.93
    stories
    -0.92
    Stories
    -0.92
     Stories
    -0.92
     fables
    -0.90
     memoirs
    -0.90
    проек
    -0.89
    POSITIVE LOGITS
     humor
    1.55
     romance
    1.41
     humour
    1.41
     twists
    1.33
     lots
    1.30
     action
    1.27
     politics
    1.23
     moral
    1.20
     unexpected
    1.18
     plenty
    1.17
    Activations Density 0.043%

    No Known Activations