© 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. 127859
    Prev
    Next
    INDEX
    Explanations

    The neuron is tuned to detect mentions of Al Qaeda and related terrorist figures or events (e.g. “bin Laden,” “Al-Qaida,” raids, killings).

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

    Al-Qaeda, Laden, commanders, operatives

    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
    ׇ
    -1.40
     ibadah
    -1.28
    -1.27
    I
    -1.27
    满是
    -1.22
     öpp
    -1.21
     Geste
    -1.20
    ἵ
    -1.16
     മ
    -1.15
     Ministero
    -1.15
    POSITIVE LOGITS
    ְּ
    1.65
    ִּ
    1.46
     červen
    1.43
    ଶ
    1.38
    ַּ
    1.38
    ְר
    1.34
    ֶּ
    1.30
     Wirken
    1.29
    ಎ
    1.27
     his
    1.26
    Activations Density 0.058%
    No Known Activations