© 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. 34-GEMMASCOPE-RES-131K
    7. 103575
    Prev
    Next
    INDEX
    Explanations

    data variable/parameter

    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_34/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
    徳島
    -0.84
    szön
    -0.76
     names
    -0.75
     results
    -0.74
     デスク
    -0.73
     dział
    -0.73
    め
    -0.73
    Dados
    -0.73
    Partici
    -0.72
    æng
    -0.72
    POSITIVE LOGITS
     from
    1.06
    quelle
    1.01
    received
    0.94
    Received
    0.89
     schrijven
    0.87
    ナップ
    0.85
    来源
    0.84
    ILA
    0.84
     samlet
    0.84
     RECEIVED
    0.83
    Activations Density 0.030%

    No Known Activations