© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92890
    Prev
    Next
    INDEX
    Explanations

    beans factory

    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
     soigne
    -0.75
     rational
    -0.73
    Ủ
    -0.72
     できる
    -0.72
    先は
    -0.72
    Qing
    -0.71
     dissociation
    -0.70
     faster
    -0.70
     töö
    -0.70
     bouch
    -0.69
    POSITIVE LOGITS
     Beans
    1.13
     beans
    1.12
    Beans
    1.05
    factory
    1.02
     factory
    0.88
     Bean
    0.86
     تجاه
    0.85
    beans
    0.83
    prof
    0.83
     bean
    0.83
    Activations Density 0.001%

    No Known Activations