© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73484
    Prev
    Next
    INDEX
    Explanations

    concessive clauses

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

    The neuron detects conditional or concessive markers—especially the word “if” (and related cues like “even if,” “albeit,” etc.) that introduce hypothetical or exception clauses.

    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
    Y
    -1.61
     but
    -1.61
     like
    -1.55
     even
    -1.55
    psi
    -1.51
    傒
    -1.40
    ">
    -1.40
    </b>
    -1.39
     ,‬
    -1.39
    _
    -1.38
    POSITIVE LOGITS
    不同的
    1.62
    sard
    1.39
     alcune
    1.39
     室内
    1.38
     количества
    1.37
     ايران
    1.34
    gruss
    1.28
    鐃
    1.25
    kamera
    1.25
    cityId
    1.24
    Activations Density 0.013%

    No Known Activations