© 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. 82470
    Prev
    Next
    INDEX
    Explanations

    border or boundary

    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
    rium
    -0.81
     Etr
    -0.75
    ֫
    -0.71
    ostock
    -0.69
    exclu
    -0.68
     lepto
    -0.67
     Ils
    -0.66
     เขา
    -0.66
    ſe
    -0.66
    Pue
    -0.65
    POSITIVE LOGITS
     border
    1.92
    border
    1.55
    Border
    1.43
     Border
    1.31
    BORDER
    1.18
     BORDER
    1.16
     Grenz
    1.09
     الحدود
    1.02
     bordering
    0.96
    boundary
    0.92
    Activations Density 0.084%

    No Known Activations