© 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. 111906
    Prev
    Next
    INDEX
    Explanations

    bit of

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

    The neuron fires on culinary quantity expressions—specifically words like “bit,” “splash,” “touch,” “dollop,” “amount,” etc., immediately followed by “of.”

    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
    ↵↵↵
    -1.66
     modalités
    -1.61
    still
    -1.61
    now
    -1.55
     tiroirs
    -1.54
     bénéfices
    -1.52
    actually
    -1.52
    never
    -1.47
    generally
    -1.45
     déplacements
    -1.45
    POSITIVE LOGITS
     nestled
    1.63
     by
    1.59
     one
    1.42
    باشد
    1.40
     subtly
    1.34
     what
    1.34
     during
    1.34
     from
    1.34
     encompasses
    1.32
     multifaceted
    1.32
    Activations Density 0.019%

    No Known Activations