© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117104
    Prev
    Next
    INDEX
    Explanations

    connecting 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_34/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
     éviter
    -1.77
     faciliter
    -1.73
     nettoyer
    -1.62
     tomber
    -1.61
     mètre
    -1.58
     apprécier
    -1.57
     attirer
    -1.55
     sourire
    -1.54
     peindre
    -1.54
     voer
    -1.52
    POSITIVE LOGITS
     which
    3.72
     but
    3.19
     as
    2.59
     since
    2.48
     while
    2.47
     thus
    2.41
     and
    2.36
     in
    2.36
     hence
    2.33
     so
    2.30
    Activations Density 0.188%

    No Known Activations