© 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. 22-GEMMASCOPE-RES-131K
    7. 65420
    Prev
    Next
    INDEX
    Explanations

    Syria and Syrian contexts

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

    The neuron strongly responds to mentions of “Syria” (and its adjective form “Syrian”) in text.

    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
    ll
    -1.57
     huit
    -1.53
    tonic
    -1.48
    ﹕
    -1.46
     nozze
    -1.46
     pureza
    -1.44
    鸶
    -1.43
     chêne
    -1.38
    times
    -1.37
     rosse
    -1.37
    POSITIVE LOGITS
     aislada
    1.49
    </b>
    1.40
     vemos
    1.37
     другими
    1.31
    第一时间
    1.27
     estaremos
    1.27
     podéis
    1.27
     numerosos
    1.25
    ILLY
    1.24
     Schließlich
    1.24
    Activations Density 0.023%

    No Known Activations