© 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. 868
    Prev
    Next
    INDEX
    Explanations

    academic degrees and contempt

    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
    摀
    -1.65
    躥
    -1.56
     interessante
    -1.46
     abd
    -1.46
     hunne
    -1.45
     représenter
    -1.44
     theſe
    -1.43
    癭
    -1.43
     モダン
    -1.42
    跑到
    -1.41
    POSITIVE LOGITS
     from
    2.34
     for
    2.27
     through
    2.22
     by
    2.11
     if
    2.02
     without
    2.00
     as
    1.86
     after
    1.78
     at
    1.76
     during
    1.75
    Activations Density 0.085%

    No Known Activations