© 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. 44003
    Prev
    Next
    INDEX
    Explanations

    not limited to

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

    The neuron strongly fires on negation and contrast markers (e.g. “not,” “but,” 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_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
     to
    -2.61
     it
    -2.06
     of
    -1.78
     where
    -1.48
     these
    -1.45
     this
    -1.41
     These
    -1.30
    你这
    -1.28
     or
    -1.26
     چیست
    -1.25
    POSITIVE LOGITS
    :”
    1.61
     البته
    1.54
     aguja
    1.50
     manguera
    1.50
    -“
    1.48
    ()");
    1.46
    lllllllll
    1.45
    ongono
    1.41
    -”
    1.39
     pegatina
    1.36
    Activations Density 0.274%

    No Known Activations