© 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. 103072
    Prev
    Next
    INDEX
    Explanations

    surgical site

    np_acts-logits-general · gemini-2.5-flash-lite

    references to military conflicts in Afghanistan and Iraq, including war-related terms and military operations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     pamięci
    -0.94
     ExecuteAsync
    -0.81
     partition
    -0.75
    Acknowled
    -0.73
     rubber
    -0.71
     estratégica
    -0.70
     Fü
    -0.69
     separation
    -0.69
     приходи
    -0.69
     takeaway
    -0.69
    POSITIVE LOGITS
     initial
    0.96
     inicial
    0.92
    initial
    0.90
     Initial
    0.89
    Initial
    0.88
     overthrow
    0.86
    初期
    0.85
     अमे
    0.84
     FFT
    0.84
    初始
    0.83
    Activations Density 0.017%

    No Known Activations