© 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. 100289
    Prev
    Next
    INDEX
    Explanations

    connecting clauses with and

    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
    Cuz
    -1.60
    Etape
    -1.55
    Matin
    -1.53
    TÜ
    -1.53
    Abit
    -1.52
    Miser
    -1.51
     ensue
    -1.50
    潁
    -1.50
    之後
    -1.48
    NATURE
    -1.48
    POSITIVE LOGITS
     was
    1.88
     of
    1.77
    on
    1.74
     and
    1.70
     weren
    1.68
     is
    1.67
     didn
    1.62
     a
    1.59
    You
    1.58
    ;?
    1.58
    Activations Density 0.053%

    No Known Activations