© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55690
    Prev
    Next
    INDEX
    Explanations

    code punctuation followed by 1

    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
     because
    -1.09
     those
    -1.02
     while
    -1.01
     quite
    -0.93
     often
    -0.93
    ｗｗｗ
    -0.91
     specifically
    -0.91
     about
    -0.91
     eight
    -0.91
     even
    -0.91
    POSITIVE LOGITS
     jednej
    1.02
     לאחר
    0.90
     suscit
    0.87
    izieren
    0.86
     composants
    0.85
    quín
    0.85
    Hadi
    0.84
     frambo
    0.84
    Sacramento
    0.83
     evenement
    0.82
    Activations Density 0.007%

    No Known Activations