© 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. 74455
    Prev
    Next
    INDEX
    Explanations

    example usages

    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
    forChild
    -1.56
     a
    -1.40
    又是一
    -1.38
    ита
    -1.36
    DataSnapshot
    -1.30
    MenuInflater
    -1.30
    ValueStyle
    -1.30
    想必
    -1.29
    誘惑
    -1.28
    啬
    -1.28
    POSITIVE LOGITS
    ↵↵
    1.70
     aña
    1.66
     of
    1.66
     réinitial
    1.64
     previamente
    1.37
    »?
    1.33
     llevo
    1.31
     gustaba
    1.31
     "#{
    1.30
     mencegah
    1.30
    Activations Density 0.033%

    No Known Activations