© 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. 34-GEMMASCOPE-RES-131K
    4. 683
    Prev
    Next
    INDEX
    Explanations

    foreign words and abbreviations

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

    The neuron responds to standalone single‐letter uppercase tokens (e.g. “K,” “M,” “E,” “R”)—typically the isolated capital letters that appear as section headings or byline initials.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    を
    -1.83
    で
    -1.65
    と
    -1.57
    が
    -1.56
    そして
    -1.55
    などの
    -1.53
     at
    -1.50
    つまり
    -1.44
    ~~
    -1.38
    但这
    -1.35
    POSITIVE LOGITS
    為に
    1.67
     glisser
    1.46
     frança
    1.45
    齜
    1.44
     valentín
    1.44
     poderosos
    1.44
    ようになります
    1.41
    際は
    1.41
     siè
    1.41
    様な
    1.40
    Activations Density 0.202%

    No Known Activations