© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69981
    Prev
    Next
    INDEX
    Explanations

    Islamist militants or terrorism

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

    The neuron fires whenever it sees a mixed-case or CamelCase identifier (e.g. HttpContext, Islamist, -*- coding -*-).

    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
    </h2>
    -2.92
    ).
    -2.70
    </h4>
    -2.36
    y
    -2.34
    咴
    -2.23
     possesses
    -2.20
    ⻄
    -2.20
    </sup>
    -2.20
    }{
    -2.14
    
    -2.13
    POSITIVE LOGITS
    ༷
    2.42
     harten
    2.27
     ouverture
    2.16
     Bestellung
    2.14
    ৢ
    2.11
     cebolla
    2.11
    棐
    2.08
     girasol
    2.05
    鶿
    2.03
     escond
    2.02
    Activations Density 0.001%

    No Known Activations