© 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. 68262
    Prev
    Next
    INDEX
    Explanations

    Cyprus, Mediterranean

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

    The neuron fires on mentions of the place “Cyprus” (and related geographic names/locations within Cyprus).

    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
     grigio
    -1.41
    duate
    -1.38
    umblr
    -1.36
    齜
    -1.36
    ahh
    -1.35
    ohh
    -1.34
     peony
    -1.34
     dahlia
    -1.32
     herbes
    -1.31
     caffè
    -1.30
    POSITIVE LOGITS
     on
    1.39
    售价
    1.37
     Cyprus
    1.33
    呖
    1.26
     could
    1.26
    晝
    1.21
     even
    1.19
    گوشی
    1.17
    𝖍
    1.17
     techniczne
    1.16
    Activations Density 0.010%

    No Known Activations