© 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. 70298
    Prev
    Next
    INDEX
    Explanations

    code punctuation and comments

    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
     kotlinx
    -0.94
    ursor
    -0.93
    恃
    -0.91
     Geschichten
    -0.89
    {?>
    -0.88
     son
    -0.88
    ≳
    -0.86
     sentimento
    -0.85
     برانيه
    -0.84
     of
    -0.84
    POSITIVE LOGITS
     //
    1.30
     –
    0.98
     -
    0.93
     (
    0.93
    íteni
    0.91
     puissiez
    0.90
    こちらも
    0.90
     lilla
    0.88
    Hướng
    0.88
     Algiers
    0.88
    Activations Density 0.008%

    No Known Activations