© 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. 76050
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    晶
    -0.72
    AML
    -0.71
    чества
    -0.69
    keln
    -0.69
    parameters
    -0.67
    <#
    -0.66
    Parameters
    -0.66
     Восто
    -0.65
     libre
    -0.65
     Barth
    -0.65
    POSITIVE LOGITS
     causal
    5.47
     causality
    4.94
     causation
    4.50
     Causal
    4.31
     Caus
    4.28
    caus
    4.25
     caus
    4.03
    Caus
    3.95
    因果
    3.70
     причин
    3.27
    Activations Density 0.182%

    No Known Activations