© 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. 22-GEMMASCOPE-RES-131K
    7. 71454
    Prev
    Next
    INDEX
    Explanations

    android code attributes

    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
     accomplish
    -0.97
    ”]
    -0.95
    olves
    -0.94
     dvě
    -0.91
     intentar
    -0.90
    цева
    -0.88
     führten
    -0.87
     habló
    -0.86
     TÉCNICA
    -0.86
     nahmen
    -0.86
    POSITIVE LOGITS
    அ
    0.88
     Regno
    0.88
     Mitarbeitern
    0.86
    의
    0.85
     Wanneer
    0.85
    Medium
    0.85
    Θ
    0.85
    ૧
    0.84
    ஜ
    0.83
    스터
    0.81
    Activations Density 0.003%

    No Known Activations