© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92811
    Prev
    Next
    INDEX
    Explanations

    Islamic State

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

    The neuron strongly activates on mentions of the Islamic State (ISIS) and related conflict-and-war vocabulary.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     FMI
    -0.83
     Forts
    -0.79
     Zhejiang
    -0.77
     UPM
    -0.76
     Chomsky
    -0.75
     DKI
    -0.71
     Itachi
    -0.71
     Rina
    -0.70
     długość
    -0.70
    enges
    -0.69
    POSITIVE LOGITS
     ISIS
    3.63
    ISIS
    2.91
     IS
    2.39
     Isis
    2.23
     داع
    1.80
     Islamic
    1.78
     Da
    1.66
    isis
    1.63
    IS
    1.62
    Da
    1.27
    Activations Density 0.039%

    No Known Activations