© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127982
    Prev
    Next
    INDEX
    Explanations

    verbs about taking action

    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
     Для
    -1.59
     And
    -1.45
     Это
    -1.44
    龔
    -1.43
     populous
    -1.39
    後記
    -1.38
    笑笑
    -1.38
    錚
    -1.36
     preocupado
    -1.36
    ⼈
    -1.33
    POSITIVE LOGITS
     of
    2.03
    2
    1.52
    3
    1.45
     now
    1.27
    的那种
    1.26
     when
    1.25
     للبيع
    1.24
    毉
    1.23
    5
    1.23
     جري
    1.20
    Activations Density 0.008%

    No Known Activations