© 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. 33770
    Prev
    Next
    INDEX
    Explanations

    karma yoga

    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
     frontline
    -0.80
    脅
    -0.79
     Front
    -0.73
    Supplied
    -0.69
    すき
    -0.69
     analysis
    -0.66
     رائعة
    -0.65
    oba
    -0.65
     仪
    -0.65
     analyses
    -0.63
    POSITIVE LOGITS
     결과
    1.16
     accumulated
    1.01
     reaction
    0.97
     резулта
    0.97
    getResult
    0.97
     results
    0.94
     bondage
    0.91
     result
    0.91
     accumulate
    0.91
     reactions
    0.90
    Activations Density 0.014%

    No Known Activations