© 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. 90151
    Prev
    Next
    INDEX
    Explanations

    switch case statements

    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
    herbe
    -0.88
    diagram
    -0.88
    eze
    -0.83
    Ἥ
    -0.83
     inconveniente
    -0.82
    avent
    -0.81
     식
    -0.80
    蒟
    -0.80
    浓郁
    -0.80
    hody
    -0.79
    POSITIVE LOGITS
     case
    2.31
    case
    2.05
     cases
    1.70
     Case
    1.45
    Case
    1.45
     caso
    1.12
    Cases
    1.10
     случае
    1.09
    cases
    1.05
    CASE
    1.04
    Activations Density 0.004%

    No Known Activations