© 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. 9884
    Prev
    Next
    INDEX
    Explanations

    Northeast + locations or UIC + collectionView

    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
    くちゃ
    -2.53
    e
    -2.25
    ндарт
    -2.17
     Roughly
    -2.16
    Unless
    -2.16
     Technically
    -2.13
    Considering
    -2.08
     "..\..\
    -2.05
    我們
    -2.05
    會有
    -2.03
    POSITIVE LOGITS
    ſelf
    2.83
    ⟞
    2.83
    »،
    2.52
    是要
    2.36
    原地
    2.36
    段时间
    2.30
     acrí
    2.30
    '
    2.22
     inteligentes
    2.20
    ：
    2.11
    Activations Density 0.003%

    No Known Activations