© 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. 10-GEMMASCOPE-RES-131K
    7. 39184
    Prev
    Next
    INDEX
    Explanations

    numerical values and scientific contexts

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

    numerical values in scientific and 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_10/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
     There
    -2.33
     since
    -2.20
     for
    -2.13
     started
    -2.06
     also
    -2.06
     or
    -2.05
     keeps
    -2.03
    The
    -2.00
     During
    -2.00
    This
    -1.99
    POSITIVE LOGITS
    齮
    1.91
     FOUR
    1.89
    齜
    1.88
     jy
    1.88
     célè
    1.85
    probably
    1.84
    both
    1.81
    often
    1.80
     vun
    1.78
    _
    1.77
    Activations Density 0.005%

    No Known Activations