© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127332
    Prev
    Next
    INDEX
    Explanations

    Springfield and associated place names

    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
     "
    -3.19
     freaking
    -3.13
    翃
    -2.48
    !!!!!!
    -2.42
     stifle
    -2.33
     crippling
    -2.30
     stroll
    -2.25
     当
    -2.25
     одной
    -2.23
    ↵
    -2.20
    POSITIVE LOGITS
     rito
    2.70
    獁
    2.58
     maría
    2.53
    牁
    2.50
     Enero
    2.48
    洐
    2.45
     Crédito
    2.44
     墊
    2.42
     nimmer
    2.42
     themſelves
    2.41
    Activations Density 0.002%

    No Known Activations