© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48995
    Prev
    Next
    INDEX
    Explanations

    ```code blocks with curly braces```

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

    The neuron activates whenever it sees standalone numeric tokens (e.g. years, version numbers, counts) in code or comments.

    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
     $('#
    -0.77
    aner
    -0.76
    trailing
    -0.70
    هد
    -0.66
    joje
    -0.65
    وست
    -0.65
    ements
    -0.65
    投手
    -0.65
     embedded
    -0.64
    éraux
    -0.64
    POSITIVE LOGITS
    rabi
    0.70
     angol
    0.68
    supervisor
    0.67
    evaluator
    0.67
     yapımı
    0.64
     Governance
    0.63
    延长
    0.63
    Willy
    0.63
     ludzi
    0.63
     extravag
    0.63
    Activations Density 0.056%

    No Known Activations