© 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. 10-GEMMASCOPE-RES-131K
    7. 111490
    Prev
    Next
    INDEX
    Explanations

    names and programming languages

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

    the surname "Guo" or names containing "Guo" as a component (particularly Chinese names and proper nouns).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on isolated capitalized tokens, i.e. proper names and named‐entity words.

    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
     The
    -2.77
     
    -2.64
    </h1>
    -2.30
     definir
    -2.23
     также
    -2.17
    氿
    -2.16
    一方で
    -2.16
    銠
    -2.13
    クソ
    -2.11
     seductive
    -2.08
    POSITIVE LOGITS
    “
    2.73
    there
    2.63
     内衣
    2.52
    ном
    2.45
    ▥
    2.44
     車場
    2.39
     crept
    2.39
    鼱
    2.38
     ヶ
    2.34
     tilby
    2.31
    Activations Density 0.009%

    No Known Activations