© 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. 10-GEMMASCOPE-RES-131K
    7. 69774
    Prev
    Next
    INDEX
    Explanations

    dosage in mg/kg or µg/kg

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

    scientific notation for dosage measurements, particularly values followed by units like "mg/kg" or "ml(-1)".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting numeric measurement values (especially decimal numbers) in scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     malen
    -1.56
     senhora
    -1.45
     социальных
    -1.41
     многое
    -1.38
    ursor
    -1.36
    躂
    -1.35
     Qaeda
    -1.32
     manifeste
    -1.31
    轻声
    -1.30
     Calculating
    -1.29
    POSITIVE LOGITS
     that
    1.54
     advice
    1.45
     when
    1.45
     of
    1.40
    2
    1.37
     including
    1.35
     DÍA
    1.34
     Absicht
    1.34
     employees
    1.29
     isnt
    1.28
    Activations Density 0.080%

    No Known Activations