© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34189
    Prev
    Next
    INDEX
    Explanations

    units of mass and quantity

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

    The neuron specializes in spotting mentions of weight or mass quantities (numbers paired with units like tons, tonnes, pounds, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    I
    -1.45
    “
    -1.41
    on
    -1.38
    M
    -1.35
     bevestig
    -1.34
     and
    -1.33
     \&
    -1.32
    ه
    -1.30
    人數
    -1.30
     or
    -1.30
    POSITIVE LOGITS
     of
    3.19
    <bos>
    2.30
    𒊹
    1.51
    俟
    1.49
    なので
    1.49
    来到了
    1.48
     чехол
    1.46
     necesar
    1.45
     {
    1.42
    +}\
    1.42
    Activations Density 0.008%

    No Known Activations