© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49240
    Prev
    Next
    INDEX
    Explanations

    numbers following 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
     when
    -1.31
     When
    -1.15
     Usually
    -1.12
     Almost
    -1.12
     using
    -1.12
     Often
    -1.07
     because
    -1.05
     what
    -1.05
     now
    -1.05
     Shortly
    -1.05
    POSITIVE LOGITS
     auffi
    1.07
    werkstatt
    1.05
     SOLUTIONS
    1.00
     ſol
    0.98
    genodigd
    0.98
     unn
    0.96
     delightfully
    0.96
     constitue
    0.96
     SESSION
    0.96
     miniaturka
    0.95
    Activations Density 0.005%

    No Known Activations