© 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. 91041
    Prev
    Next
    INDEX
    Explanations

    horizontal divider lines

    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
     buttons
    -0.84
    mayacak
    -0.80
    jungan
    -0.77
     button
    -0.74
    shadowRadius
    -0.74
    prism
    -0.72
    ことが
    -0.71
     typeface
    -0.71
    labelledby
    -0.71
     asupra
    -0.71
    POSITIVE LOGITS
    drawLine
    1.38
     LINE
    1.25
    เส้น
    1.22
     line
    1.21
    DrawLine
    1.17
     horizontal
    1.12
     Line
    1.11
     lines
    1.10
     線
    1.09
     Horizontal
    1.09
    Activations Density 0.011%

    No Known Activations