© 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. 69525
    Prev
    Next
    INDEX
    Explanations

    take something

    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
    3
    -1.73
    including
    -1.72
     are
    -1.68
    しばらく
    -1.66
    𓆜
    -1.50
     $-\
    -1.46
     takiego
    -1.45
     {
    -1.45
    0
    -1.43
    8
    -1.41
    POSITIVE LOGITS
    dö
    1.54
    dags
    1.48
    anderen
    1.38
     其他
    1.34
    Cubit
    1.34
    grafos
    1.31
    诒
    1.28
    bá
    1.27
    𖤍
    1.25
    duh
    1.24
    Activations Density 0.016%

    No Known Activations