© 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. 78847
    Prev
    Next
    INDEX
    Explanations

    quantum-classical correspondence

    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
    ---*/
    -0.91
    λευ
    -0.87
    anderen
    -0.82
    ⇆
    -0.80
    フォーマンス
    -0.77
     Swartz
    -0.77
    護
    -0.76
     ARTISTS
    -0.75
    ächtig
    -0.74
    ܵ
    -0.74
    POSITIVE LOGITS
     classical
    4.97
    classical
    4.31
    Classical
    3.92
     Classical
    3.91
     класси
    2.91
     klassischen
    2.67
    古典
    2.67
     класи
    2.64
     classique
    2.59
     klassische
    2.56
    Activations Density 0.084%

    No Known Activations