© 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. 10-GEMMASCOPE-RES-131K
    4. 85015
    Prev
    Next
    INDEX
    Explanations

    list terminators such as `.` or `!`

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

    The neuron activates on numeric tokens (integers or decimals), i.e. numbers embedded in the text.

    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
    了很多
    -2.36
    </h1>
    -2.36
    了许多
    -2.27
    ignent
    -2.23
    ⬯
    -2.23
    Джере
    -2.05
    结语
    -2.00
     और
    -1.99
    沨
    -1.98
    ྅
    -1.98
    POSITIVE LOGITS
    of
    2.22
     Each
    2.09
     Of
    2.08
     Would
    2.06
     OF
    2.06
     When
    2.05
     bellissima
    1.98
     It
    1.97
    琉
    1.92
     surgir
    1.89
    Activations Density 0.001%

    No Known Activations