© 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. 113447
    Prev
    Next
    INDEX
    Explanations

    Yet followed by contrasting information

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

    This neuron detects the contrastive discourse marker “yet” when it begins a sentence or clause.

    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
     and
    -2.42
    </h2>
    -2.16
    ");
    -2.14
    ");
    -1.95
    ”,
    -1.93
     stycznia
    -1.90
    覓
    -1.88
    ”.
    -1.86
     fria
    -1.84
    er
    -1.83
    POSITIVE LOGITS
     verhind
    2.61
     gebeten
    2.23
     gewisse
    2.23
     reizen
    2.19
    malige
    2.17
     berichten
    2.06
     we
    2.06
    CHREIB
    2.02
     potret
    1.98
     tatsächlich
    1.95
    Activations Density 0.004%

    No Known Activations