© 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. 103882
    Prev
    Next
    INDEX
    Explanations

    date and time

    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
     rainha
    -1.61
     senhora
    -1.49
     menina
    -1.35
     filha
    -1.34
     solteiro
    -1.31
     irmã
    -1.27
    ってみました
    -1.27
     estrada
    -1.26
     noiva
    -1.25
     consultez
    -1.25
    POSITIVE LOGITS
    Would
    1.48
    would
    1.37
     –
    1.34
     and
    1.23
    = 
    1.20
     utilisant
    1.20
     gibt
    1.20
     ذه
    1.20
    It
    1.20
    Wouldn
    1.19
    Activations Density 0.084%

    No Known Activations