© 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. 58270
    Prev
    Next
    INDEX
    Explanations

    fortress and populace

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

    The neuron responds specifically to occurrences of the word “fortress.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵↵
    -3.27
    ଃ
    -2.97
    尨
    -2.64
    1
    -2.56
    殽
    -2.53
    (
    -2.53
    \
    -2.28
    虓
    -2.28
    鈁
    -2.28
     synergies
    -2.27
    POSITIVE LOGITS
    </strong>
    3.13
     It
    3.02
     dificuldades
    2.77
    と思われます
    2.41
    …！
    2.39
    鵡
    2.34
    //}
    2.33
    </h3>
    2.33
     ก็
    2.30
     identifiés
    2.30
    Activations Density 0.007%

    No Known Activations