© 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. 90455
    Prev
    Next
    INDEX
    Explanations

    skating sports and lessons

    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
    a
    -2.91
     представителей
    -2.61
    鸲
    -2.58
    氿
    -2.48
     "
    -2.48
    𝄆
    -2.45
     `
    -2.44
    ኧ
    -2.44
     call
    -2.44
     *
    -2.44
    POSITIVE LOGITS
     evidenced
    2.69
    琤
    2.61
    崃
    2.48
    ية
    2.45
    Even
    2.41
    \%)
    2.39
     contextLoads
    2.39
    With
    2.38
    ,”
    2.38
    Because
    2.36
    Activations Density 0.002%

    No Known Activations