© 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. 12275
    Prev
    Next
    INDEX
    Explanations

    Python code snippets

    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
     relacionamento
    -1.00
    皤
    -0.88
     separados
    -0.86
     kreis
    -0.84
    查看
    -0.82
    压力
    -0.82
     llega
    -0.81
    发布时间
    -0.81
     في
    -0.80
    Separ
    -0.80
    POSITIVE LOGITS
    èo
    0.85
    قرير
    0.84
     チェック
    0.84
     Quoted
    0.82
     Andorra
    0.81
    مرار
    0.78
    ższy
    0.77
     アルバム
    0.77
    娅
    0.76
    ceptives
    0.76
    Activations Density 0.003%

    No Known Activations