© 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. 81727
    Prev
    Next
    INDEX
    Explanations

    produced, directed, composed, wrote

    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
     celebró
    -0.96
    кій
    -0.95
     має
    -0.85
    问我
    -0.84
     sostuvo
    -0.83
     prédio
    -0.82
     publicó
    -0.81
     establishing
    -0.81
    focus
    -0.78
    зовые
    -0.78
    POSITIVE LOGITS
    เป็น
    1.15
    担任
    1.09
    擔任
    1.06
     offic
    1.04
     diriger
    0.94
     acts
    0.92
     cerveja
    0.91
     act
    0.90
     supervise
    0.90
     narr
    0.88
    Activations Density 0.060%

    No Known Activations