© 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. 12149
    Prev
    Next
    INDEX
    Explanations

    international and domain 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_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
    ̵
    -1.05
     alterar
    -0.90
    Mixin
    -0.88
     +
    -0.88
    ziali
    -0.87
     personnelles
    -0.86
    vejec
    -0.85
     диски
    -0.84
     wok
    -0.84
    进了
    -0.84
    POSITIVE LOGITS
     中國
    0.93
    theatre
    0.91
     political
    0.90
    entuh
    0.89
     劉
    0.89
     نہیں
    0.87
     儿童
    0.86
     even
    0.86
     økonom
    0.84
     Именно
    0.84
    Activations Density 0.199%

    No Known Activations