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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12344
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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_22/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
    だけでなく
    -1.20
     ווע
    -1.19
    だけではなく
    -1.18
     Não
    -1.11
    即是
    -1.09
    屃
    -1.09
    だけでは
    -1.08
    eroon
    -1.07
    liege
    -1.05
     leſs
    -1.02
    POSITIVE LOGITS
    فیلم
    1.41
     that
    1.40
    مدیر
    1.20
     vilja
    1.16
    sowie
    1.15
    ถ้า
    1.14
     MonoBehaviour
    1.09
    Город
    1.06
    مرا
    1.05
    Теле
    1.03
    Activations Density 0.022%

    No Known Activations