© 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. 83608
    Prev
    Next
    INDEX
    Explanations

    adding elements to ui

    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
    --
    -0.92
     for
    -0.87
    &
    -0.84
    ˌ
    -0.80
     "
    -0.79
    "
    -0.79
    ...
    -0.78
     refiri
    -0.76
     ребенку
    -0.76
     Hi
    -0.75
    POSITIVE LOGITS
    addChild
    1.16
     aumentar
    1.02
     decorativa
    0.95
     pierna
    0.94
    appendChild
    0.92
     fluido
    0.92
    氦
    0.90
    添加到
    0.89
     emisiones
    0.89
    מוס
    0.88
    Activations Density 0.014%

    No Known Activations