© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116714
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

    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
     Orgel
    -0.79
    ському
    -0.70
    
    -0.69
    の声
    -0.69
     traces
    -0.67
     любого
    -0.67
    \[
    -0.66
     seguinte
    -0.65
     campos
    -0.65
    FLAG
    -0.65
    POSITIVE LOGITS
     한다
    0.73
    setRotation
    0.73
    Thir
    0.69
    처럼
    0.67
     Gree
    0.67
    Liqu
    0.66
    setLine
    0.65
     piercings
    0.65
     jumpers
    0.65
    Reno
    0.65
    Activations Density 0.050%

    No Known Activations