© 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. 22-GEMMASCOPE-RES-131K
    7. 66186
    Prev
    Next
    INDEX
    Explanations

    country names and organizations

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

    The neuron spots mentions of countries (and their abbreviations or demonyms).

    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
     from
    -1.59
    )}
    -1.37
    ‌.
    -1.30
     that
    -1.27
    )("
    -1.25
    zzet
    -1.24
     akrab
    -1.23
    >),
    -1.23
     ។
    -1.21
     velas
    -1.21
    POSITIVE LOGITS
    '
    1.48
    _
    1.27
     has
    1.25
    ’
    1.22
    ９
    1.13
    .
    1.10
     ativar
    1.09
    不一樣
    1.04
    ｗｗ
    1.03
    度に
    1.03
    Activations Density 0.098%

    No Known Activations