© 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. 9573
    Prev
    Next
    INDEX
    Explanations

    complete with features

    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
     gustado
    -1.99
    氿
    -1.59
    外界
    -1.59
     آنجا
    -1.54
    に入れる
    -1.54
     regroupe
    -1.52
    屃
    -1.51
    へ行
    -1.50
    咋
    -1.50
     jeżeli
    -1.45
    POSITIVE LOGITS
    In
    2.09
    Some
    1.88
    Ironically
    1.86
    Although
    1.84
    Surprisingly
    1.80
    although
    1.77
    Even
    1.76
    Just
    1.75
    They
    1.75
    Considering
    1.71
    Activations Density 0.006%

    No Known Activations