© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12945
    Prev
    Next
    INDEX
    Explanations

    magical objects or items

    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
    those
    -1.55
     THOSE
    -1.44
     například
    -1.43
    殃
    -1.40
    compati
    -1.34
    these
    -1.32
    Жит
    -1.30
    newList
    -1.27
    gerichte
    -1.27
     krijgen
    -1.27
    POSITIVE LOGITS
     bagay
    1.48
    viembre
    1.48
     osal
    1.40
     eikä
    1.34
     ramos
    1.32
    IZED
    1.32
     diário
    1.31
    ಕ್ಕ
    1.30
     from
    1.27
     asisten
    1.27
    Activations Density 0.065%

    No Known Activations