© 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. 73933
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The neuron fires on standalone document‐identifying numbers (e.g. order numbers, section/publication IDs, reference labels and similar numeric identifiers).

    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
    It
    -0.91
    Véxase
    -0.88
    􀀀
    -0.85
    ONI
    -0.82
     jusque
    -0.78
    截图
    -0.77
     bensin
    -0.77
    But
    -0.77
     pittores
    -0.77
     запись
    -0.76
    POSITIVE LOGITS
     sedang
    1.10
     month
    1.02
    ij
    0.97
    Pendant
    0.94
    })`
    0.92
     season
    0.88
     když
    0.86
    offsetHeight
    0.86
    Ekster
    0.85
    }}{{
    0.85
    Activations Density 0.024%

    No Known Activations