© 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. 92929
    Prev
    Next
    INDEX
    Explanations

    arthroscopic fluid collection pouches

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

    sentence beginnings that follow punctuation marks or paragraph breaks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on tokens that are plural or possessive forms—i.e. words ending in “s” (including “’s” or just “s”).

    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
     virtuel
    -1.00
     tragé
    -0.99
     fiables
    -0.97
    婓
    -0.96
     剤
    -0.95
     kreat
    -0.94
     fantastisk
    -0.94
     gré
    -0.94
     donar
    -0.93
     médi
    -0.92
    POSITIVE LOGITS
     They
    1.23
    見ると
    1.13
     "`
    1.07
     More
    1.02
     --
    1.02
     `
    0.97
    出てくる
    0.96
    だか
    0.96
     erste
    0.94
     slutet
    0.93
    Activations Density 0.171%

    No Known Activations