© 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. 1883
    Prev
    Next
    INDEX
    Explanations

    stiffness

    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
    er
    -2.80
    ꯶
    -2.41
    
    -2.31
     شیپور
    -2.27
    蟥
    -2.22
    {
    -2.20
    t
    -2.14
     visionary
    -2.14
     現在
    -2.13
    囿
    -2.09
    POSITIVE LOGITS
    0
    2.66
    6
    2.56
    4
    2.48
    3
    2.41
    .
    2.27
    also
    2.17
     )
    2.14
    ）
    2.13
    ,"
    2.11
    and
    2.08
    Activations Density 0.003%

    No Known Activations