© 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. 129961
    Prev
    Next
    INDEX
    Explanations

    each [noun]

    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
     he
    -1.47
     또
    -1.44
    so
    -1.42
     alguns
    -1.41
    la
    -1.41
     Then
    -1.41
    still
    -1.40
    he
    -1.38
     kleinen
    -1.37
     senza
    -1.36
    POSITIVE LOGITS
     facilitates
    1.82
     bolí
    1.77
     our
    1.75
    さてさて
    1.71
     encompasses
    1.70
     every
    1.69
    そういえば
    1.69
     biela
    1.68
     joga
    1.65
    それにしても
    1.64
    Activations Density 0.030%

    No Known Activations