© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14839
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relative clauses

    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
     !!!!
    -3.72
     soooo
    -3.55
     !!!!!
    -3.48
     Dinas
    -3.47
    神情
    -3.36
     insanely
    -3.34
     😁
    -3.27
     .......
    -3.22
     pivotal
    -3.20
     ........
    -3.17
    POSITIVE LOGITS
     or
    4.75
     at
    4.22
     even
    4.13
     if
    4.00
     on
    3.70
     with
    3.58
     as
    3.58
     distinctly
    3.55
     although
    3.55
     because
    3.53
    Activations Density 2.599%

    No Known Activations