© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108909
    Prev
    Next
    INDEX
    Explanations

    "In my", "Design &", "Pharmaceutical", "Q:", "The author"

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

    decimal numbers in technical or mathematical contexts.

    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
     these
    -0.93
    byen
    -0.85
     now
    -0.84
     جاده
    -0.82
     subtropical
    -0.81
    HasForeignKey
    -0.79
    Lif
    -0.79
     persiapan
    -0.79
     most
    -0.79
     authors
    -0.78
    POSITIVE LOGITS
     estrateg
    0.89
     problemas
    0.85
     từ
    0.83
    本当に
    0.82
    onymus
    0.81
     pronon
    0.80
     tướng
    0.79
    ठी
    0.79
    ända
    0.79
     elige
    0.78
    Activations Density 0.004%

    No Known Activations