© 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. 34-GEMMASCOPE-RES-131K
    7. 48782
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
     inconnu
    -1.02
    İL
    -1.01
    σία
    -0.94
     doar
    -0.91
     pés
    -0.91
     cucchiaio
    -0.90
    презента
    -0.90
     hiciera
    -0.88
    //'
    -0.88
    затор
    -0.88
    POSITIVE LOGITS
     therefore
    1.42
     Therefore
    1.27
     which
    1.18
     since
    1.05
     so
    1.02
     whom
    1.02
     also
    1.02
     now
    1.00
     then
    0.98
     Moreover
    0.96
    Activations Density 0.005%

    No Known Activations