© 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. 113950
    Prev
    Next
    INDEX
    Explanations

    religious buildings

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

    The neuron activates on occurrences of the word “temple,” identifying mentions of a temple or temples in the text.

    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
    '
    -2.42
    鐿
    -2.23
    大半
    -2.22
    ឵
    -2.14
     \&
    -2.02
     важно
    -1.99
     этапе
    -1.98
    傒
    -1.95
    ễn
    -1.93
    šiť
    -1.89
    POSITIVE LOGITS
    at
    2.88
    <i>
    2.58
    </b>
    2.30
    It
    2.27
    g
    2.16
    ありますが
    2.14
    𐍆
    2.13
    c
    2.08
     adding
    1.95
    <bos>
    1.93
    Activations Density 0.007%

    No Known Activations