© 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. 10-GEMMASCOPE-RES-131K
    7. 128881
    Prev
    Next
    INDEX
    Explanations

    between two entities

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

    This neuron primarily detects occurrences of the word “between.”

    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
     '
    -2.02
     אשר
    -1.52
    </b>
    -1.47
    芻
    -1.45
    )))),
    -1.43
     offer
    -1.42
    tidumbre
    -1.42
    raisals
    -1.38
    --"
    -1.37
     pronounce
    -1.35
    POSITIVE LOGITS
    すっ
    1.75
    Jeden
    1.68
     qualifié
    1.65
    Бил
    1.64
     seolah
    1.62
     знаю
    1.59
    Wirtschaft
    1.59
     soyez
    1.58
    liegende
    1.57
     dezen
    1.54
    Activations Density 0.032%

    No Known Activations