© 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. 2239
    Prev
    Next
    INDEX
    Explanations

    vertical lines and stripes

    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
    ើ
    -0.87
    ಿಕ
    -0.86
    toplas
    -0.84
    woff
    -0.76
    efel
    -0.75
    getUrl
    -0.75
     Spherical
    -0.74
    מוד
    -0.73
     globular
    -0.73
    roblast
    -0.73
    POSITIVE LOGITS
     lines
    2.88
     Lines
    2.06
    Lines
    1.99
     line
    1.98
    lines
    1.96
     líneas
    1.95
     stripes
    1.94
     parallel
    1.76
     linhas
    1.70
     LINES
    1.58
    Activations Density 0.084%

    No Known Activations