© 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. 206
    Prev
    Next
    INDEX
    Explanations

    last names of people

    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
     himself
    -1.77
     with
    -1.56
    DESCRIPCIÓN
    -1.47
     on
    -1.47
     ewigen
    -1.46
     italiano
    -1.45
     stipend
    -1.43
     Definitely
    -1.40
    Эти
    -1.39
    aien
    -1.37
    POSITIVE LOGITS
     herself
    2.41
    让他
    1.41
     bint
    1.38
     cso
    1.38
     tejidos
    1.37
     exceedingly
    1.37
    esh
    1.36
    
    1.35
     quando
    1.34
     bocetos
    1.34
    Activations Density 0.129%

    No Known Activations