© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91422
    Prev
    Next
    INDEX
    Explanations

    Public service and official roles

    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
    terraform
    -0.74
    ̒
    -0.73
    StringProperty
    -0.73
     क्ष
    -0.70
     paga
    -0.70
     lú
    -0.70
     heterogeneity
    -0.69
     écla
    -0.69
     público
    -0.69
     tej
    -0.69
    POSITIVE LOGITS
     Input
    0.86
     Option
    0.79
     option
    0.78
    牀
    0.78
    rtype
    0.77
     Comment
    0.77
     радио
    0.76
    Input
    0.76
     safety
    0.76
     schools
    0.75
    Activations Density 0.025%

    No Known Activations