© 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. 10-GEMMASCOPE-RES-131K
    7. 59866
    Prev
    Next
    INDEX
    Explanations

    ds followed by punctuation or specific codes

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

    The neuron consistently fires on tokens beginning with “ds” (typically followed by digits).

    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
    .
    -3.64
    ～。
    -2.95
     })
    -2.59
    ～　
    -2.59
     EVALU
    -2.52
    禤
    -2.47
    𓄹
    -2.47
    ～♪
    -2.47
    柃
    -2.44
    itarianism
    -2.42
    POSITIVE LOGITS
    y
    3.20
     '
    2.95
     wichtigste
    2.89
     `
    2.81
    ",
    2.81
    \
    2.64
    ',
    2.64
    u
    2.61
    "—
    2.56
     usual
    2.55
    Activations Density 0.006%

    No Known Activations