© 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. 83349
    Prev
    Next
    INDEX
    Explanations

    foreign languages and code snippets

    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
    entier
    -1.01
    リの
    -0.79
     konnte
    -0.76
    ặt
    -0.74
    кости
    -0.71
    iş
    -0.70
     Bohn
    -0.70
     Dieser
    -0.70
     התק
    -0.69
    中毒
    -0.69
    POSITIVE LOGITS
     粉色
    1.02
    voici
    1.00
    เป๋า
    0.90
    needs
    0.89
    Etape
    0.85
     MAI
    0.84
    Autres
    0.84
    ativamente
    0.84
    forgot
    0.83
     tôm
    0.83
    Activations Density 0.001%

    No Known Activations