© 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. 15434
    Prev
    Next
    INDEX
    Explanations

    HTML/code closing delimiters

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

    The neuron is primarily detecting numeric tokens (e.g. numeric literals and measurements) in code and markup.

    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
     vodu
    -1.19
     bouteilles
    -1.09
     šed
    -1.09
     goûts
    -1.04
     équipé
    -1.01
     farby
    -1.00
    饯
    -1.00
     arbres
    -1.00
     černé
    -0.99
     夾
    -0.98
    POSITIVE LOGITS
     it
    0.99
     its
    0.93
     $
    0.93
    وروبا
    0.92
    。
    0.91
     https
    0.91
    ։
    0.91
    mousemove
    0.91
     their
    0.91
     will
    0.91
    Activations Density 0.046%

    No Known Activations