© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117204
    Prev
    Next
    INDEX
    Explanations

    drawing lines, tracks, borders

    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
    HORIZONTAL
    -0.84
     gefragt
    -0.82
    PAREN
    -0.81
     男女
    -0.79
     Paragraph
    -0.79
     horaires
    -0.79
     astronom
    -0.78
     Bemerkungen
    -0.78
    VERTICAL
    -0.77
     obliquely
    -0.77
    POSITIVE LOGITS
     lines
    1.41
     visualization
    1.38
     Lines
    1.35
     visualize
    1.20
     dashed
    1.20
     debug
    1.19
     arrows
    1.18
     wire
    1.17
     line
    1.15
     highlighting
    1.15
    Activations Density 0.026%

    No Known Activations