© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118783
    Prev
    Next
    INDEX
    Explanations

    include / includes / destination

    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
    ρισσότε
    -0.88
    Campe
    -0.74
    픈
    -0.73
     võimal
    -0.71
    ẤT
    -0.71
    JAXB
    -0.70
     志
    -0.69
    kmal
    -0.69
     ouders
    -0.68
    flexGrow
    -0.68
    POSITIVE LOGITS
     include
    5.09
    include
    4.69
     inclusion
    4.44
     Include
    4.41
    Include
    4.28
     included
    4.28
     includes
    3.80
     inclusions
    3.67
     Inclusion
    3.67
     INCLUDE
    3.59
    Activations Density 0.338%

    No Known Activations