© 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. 103606
    Prev
    Next
    INDEX
    Explanations

    first and foremost

    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
     påvir
    -1.50
    罍
    -1.49
     kaikki
    -1.48
    værende
    -1.48
    sukienka
    -1.45
    ඞ
    -1.45
     nini
    -1.45
     PHILADELPHIA
    -1.44
     queridos
    -1.41
     determinar
    -1.38
    POSITIVE LOGITS
     of
    1.98
     from
    1.83
    8
    1.80
    7
    1.79
    5
    1.68
     To
    1.68
     like
    1.63
    6
    1.63
     on
    1.63
     for
    1.63
    Activations Density 0.031%

    No Known Activations