© 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. 2105
    Prev
    Next
    INDEX
    Explanations

    bean creation and context

    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
     الرياضيه
    -0.69
     réseau
    -0.68
     constructive
    -0.68
    榕
    -0.68
     network
    -0.68
    BadRequest
    -0.68
    ennom
    -0.67
     Ol
    -0.67
     TAP
    -0.66
     Sah
    -0.65
    POSITIVE LOGITS
     beans
    4.66
     bean
    4.31
    Bean
    3.75
     Bean
    3.70
    bean
    3.69
    beans
    3.67
     Beans
    3.67
    Beans
    3.38
    BEAN
    2.86
    getBean
    2.69
    Activations Density 0.062%

    No Known Activations