© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92181
    Prev
    Next
    INDEX
    Explanations

    one followed by a word

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

    The neuron activates on the second word of multi‐word “One …” phrases or titles (e.g. Hit in “One Hit Wonders,” Shot in “One Shot…,” Size in “One‐Size‐Fits‐All,” Day in “One Day…,” etc.).

    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
    0
    -1.11
    少しずつ
    -0.95
    確認ください
    -0.94
    怎麼辦
    -0.89
     Sprachen
    -0.88
    ]='\
    -0.87
    不一樣
    -0.86
     FormGroup
    -0.86
    一開始
    -0.85
    Categoría
    -0.84
    POSITIVE LOGITS
     wonders
    1.26
     dois
    1.05
     wonder
    0.95
    ☝
    0.93
     One
    0.91
     takut
    0.89
    eador
    0.87
     Wonder
    0.87
    RECEIVE
    0.87
    mio
    0.86
    Activations Density 0.042%

    No Known Activations