© 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. 78618
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and connectors

    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
     coté
    -1.78
     parlement
    -1.77
     appliquer
    -1.76
     estadounid
    -1.72
     sourire
    -1.71
     mètre
    -1.69
     corriger
    -1.68
     inkluder
    -1.64
     derni
    -1.63
     dessous
    -1.62
    POSITIVE LOGITS
     which
    5.38
     as
    3.33
     but
    3.20
     and
    2.91
     while
    2.81
     or
    2.75
     including
    2.72
     although
    2.70
     with
    2.67
     for
    2.48
    Activations Density 0.299%

    No Known Activations