© 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. 68250
    Prev
    Next
    INDEX
    Explanations

    Yersinia pseudotuberculosis, predicted

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

    mathematical expressions and symbols in technical equations.

    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_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
    fotografie
    -1.09
     misschien
    -1.05
     nacido
    -1.02
     Cette
    -0.98
    cended
    -0.98
     rayures
    -0.98
     motoru
    -0.98
     énorm
    -0.97
    ₓ
    -0.96
     Перейти
    -0.96
    POSITIVE LOGITS
     while
    1.13
     from
    1.00
     indeed
    0.96
     using
    0.90
     must
    0.90
     since
    0.90
     out
    0.88
     because
    0.86
     standard
    0.86
     voila
    0.83
    Activations Density 0.014%

    No Known Activations