© 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. 10-GEMMASCOPE-RES-131K
    7. 1254
    Prev
    Next
    INDEX
    Explanations

    physical and metaphorical walls

    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_10/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
     then
    -2.91
     was
    -2.86
    ceptable
    -2.77
    gencias
    -2.75
    breviations
    -2.73
    igrette
    -2.72
    晔
    -2.70
    iarkan
    -2.63
    行
    -2.61
     dataGridView
    -2.59
    POSITIVE LOGITS
    "
    3.31
    僅
    3.28
    -
    2.89
    是
    2.81
    ↵
    2.78
     
    2.77
    CHREIB
    2.58
    事も
    2.53
    とても
    2.53
     walls
    2.52
    Activations Density 0.007%

    No Known Activations