© 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. 10-GEMMASCOPE-RES-131K
    7. 128091
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    The neuron fires on tokens that are acronyms or identifiers containing uppercase letters (e.g. all-caps abbreviations or CamelCase names).

    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
    }$
    -2.30
    емом
    -2.28
    +};
    -2.27
     تعدى
    -2.27
    檠
    -2.25
    大声
    -2.23
    athies
    -2.22
    loride
    -2.17
     multitude
    -2.14
     termed
    -2.14
    POSITIVE LOGITS
    i
    3.58
    い
    2.53
    al
    2.48
    阏
    2.47
    2.42
    ・・・。
    2.41
    鹮
    2.41
    냑
    2.39
    >
    2.27
     حدود
    2.17
    Activations Density 0.002%
    No Known Activations