© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    read operations

    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
    f
    -1.69
     représentation
    -1.42
     “
    -1.36
    itados
    -1.28
     begge
    -1.27
     («
    -1.25
    iological
    -1.25
    檐
    -1.23
     eterna
    -1.23
     כמו
    -1.22
    POSITIVE LOGITS
     the
    1.87
    ⤹
    1.59
     nacidos
    1.48
     sentía
    1.43
     creía
    1.42
    欷
    1.41
     ходить
    1.41
    CurtirCurtir
    1.39
    usure
    1.39
     at
    1.38
    Activations Density 0.021%

    No Known Activations