© 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. 54285
    Prev
    Next
    INDEX
    Explanations

    spectral line width

    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
     потен
    -0.79
    IGN
    -0.76
    geslacht
    -0.73
     explí
    -0.72
    Distances
    -0.70
    savevideo
    -0.68
    ijn
    -0.68
     Rä
    -0.68
     pObj
    -0.67
     aiutare
    -0.67
    POSITIVE LOGITS
     width
    2.73
     broadening
    2.34
     widths
    2.28
    width
    2.23
     Width
    2.13
    Width
    2.03
     broaden
    1.88
     broadened
    1.85
     шири
    1.66
    WIDTH
    1.64
    Activations Density 0.048%

    No Known Activations