© 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. 118452
    Prev
    Next
    INDEX
    Explanations

    granular gases

    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
    Defender
    -0.84
     Defenders
    -0.74
    ႈ
    -0.68
     Abou
    -0.68
    هاء
    -0.67
     equipments
    -0.67
     Defender
    -0.67
    uso
    -0.66
     製
    -0.65
     získ
    -0.65
    POSITIVE LOGITS
    мара
    0.69
    efficient
    0.69
     writing
    0.68
     雷
    0.68
    一行
    0.67
     Root
    0.66
    vaila
    0.66
     dö
    0.66
    DESIGN
    0.65
     непре
    0.65
    Activations Density 0.103%

    No Known Activations