© 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. 10-GEMMASCOPE-RES-131K
    7. 72413
    Prev
    Next
    INDEX
    Explanations

    IS, ISIS, State

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

    The neuron strongly activates for mentions of the Islamic State (ISIS/ISIL) or its variants.

    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
    ẳn
    -1.58
    Should
    -1.51
    ?
    -1.47
    ～　
    -1.46
    The
    -1.46
    It
    -1.45
    When
    -1.43
     sheds
    -1.41
    Open
    -1.36
    For
    -1.34
    POSITIVE LOGITS
     invitamos
    1.57
    чними
    1.49
    ௜
    1.43
    ÈME
    1.43
     лампа
    1.41
    Ⅷ
    1.41
    ꠥ
    1.40
     direkte
    1.39
     kuchni
    1.37
     distinto
    1.36
    Activations Density 0.006%

    No Known Activations