© 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. 42665
    Prev
    Next
    INDEX
    Explanations

    sci-fi and horror movie titles

    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_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
     there
    -1.77
     like
    -1.35
     seperti
    -1.24
     эту
    -1.23
     this
    -1.16
    “-
    -1.12
    та
    -1.11
     occidentalis
    -1.11
    you
    -1.09
    “)
    -1.09
    POSITIVE LOGITS
    èses
    1.20
     treinamento
    1.20
    ONLY
    1.19
    aknya
    1.19
     be
    1.18
     verbo
    1.15
    livé
    1.14
     desenvolvimento
    1.13
     anúncio
    1.13
     prazo
    1.12
    Activations Density 0.020%

    No Known Activations