© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71970
    Prev
    Next
    INDEX
    Explanations

    sandwiched between

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

    The neuron responds to references to “sandwich”‐type structures—that is, terms like sandwich, sandwiched, or caught/bonded “between” two layers.

    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
    .
    -1.84
    {
    -1.79
     Preguntas
    -1.70
    其
    -1.65
     actually
    -1.65
    の部分
    -1.60
     Años
    -1.59
    <strong>
    -1.58
    an
    -1.57
    尛
    -1.56
    POSITIVE LOGITS
    以上です
    1.86
    不僅
    1.77
    ではでは
    1.71
     impede
    1.70
     BOTH
    1.70
     hardships
    1.70
     erode
    1.66
    ⑊
    1.64
    änemark
    1.64
     échange
    1.59
    Activations Density 0.010%

    No Known Activations