© 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. 22-GEMMASCOPE-RES-131K
    7. 127681
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the word “wall” (in compound terms or standalone) throughout the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    wall followed by descriptive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ’
    -2.92
     帶
    -2.81
    ”
    -2.52
    ꯳
    -2.42
    絰
    -2.25
    贗
    -2.25
    瑧
    -2.23
    儈
    -2.17
     當
    -2.06
    which
    -2.05
    POSITIVE LOGITS
    𓆜
    2.75
     '
    2.63
    '),
    2.52
     pejabat
    2.39
    柽
    2.34
     esteemed
    2.23
     respective
    2.22
     indispensable
    2.22
    </u>
    2.20
    ),"
    2.20
    Activations Density 0.017%

    No Known Activations