© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73515
    Prev
    Next
    INDEX
    Explanations

    code block endings

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

    The neuron activates on standalone numeric literals (numbers) in code snippets.

    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
     of
    -1.98
     for
    -1.57
     to
    -1.15
     from
    -1.11
     a
    -1.05
     those
    -1.02
     as
    -1.02
     biografias
    -1.02
     by
    -1.02
    SceneManagement
    -0.99
    POSITIVE LOGITS
    ⌓
    1.05
    之間
    1.01
    Ciri
    1.00
     Freire
    1.00
    必须要
    1.00
    柟
    0.98
    among
    0.96
     hermosos
    0.96
     ism
    0.96
     amables
    0.95
    Activations Density 0.013%

    No Known Activations