© 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. 40896
    Prev
    Next
    INDEX
    Explanations

    Q prefix

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

    The neuron specifically responds to the word “and.”

    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
     Tidak
    -1.60
    ехали
    -1.55
    𝐅
    -1.51
     temporaire
    -1.45
     travaille
    -1.45
    žiaga
    -1.42
     Aplikasi
    -1.40
     Seperti
    -1.39
    ală
    -1.38
    ïe
    -1.38
    POSITIVE LOGITS
     how
    2.31
     have
    1.99
     such
    1.80
     its
    1.71
    n
    1.67
    o
    1.64
    c
    1.61
     also
    1.58
    </h1>
    1.53
     everything
    1.52
    Activations Density 0.000%

    No Known Activations