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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104550
    Prev
    Next
    INDEX
    Explanations

    Islamic terms

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

    The neuron specializes in spotting references to Islam and Muslim religious terms, events, and places.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ..,
    -1.34
    0
    -1.29
     wuß
    -1.28
    ,;
    -1.27
    -,
    -1.27
     giebt
    -1.16
    ,:
    -1.15
     fragte
    -1.15
     meinem
    -1.14
     ;-
    -1.14
    POSITIVE LOGITS
    )।
    1.43
    mice
    1.34
    AILY
    1.29
     andet
    1.24
    Rujukan
    1.19
    ಆ
    1.18
    ஹ
    1.17
    ॰
    1.16
    zzá
    1.16
    bronn
    1.15
    Activations Density 0.039%

    No Known Activations