© 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. 103764
    Prev
    Next
    INDEX
    Explanations

    code start 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
     těchto
    -1.17
    tamanho
    -1.05
    waterproof
    -0.97
    彼らの
    -0.92
    These
    -0.89
     této
    -0.89
    馒
    -0.87
    INDICE
    -0.87
    Abbildung
    -0.86
    CARACTERIST
    -0.85
    POSITIVE LOGITS
     республи
    1.02
    VENTION
    0.96
    스트
    0.96
    QUE
    0.94
    制的
    0.93
    БО
    0.90
    АН
    0.89
     MAR
    0.87
    СТА
    0.87
    CAR
    0.86
    Activations Density 0.088%

    No Known Activations