© 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. 33142
    Prev
    Next
    INDEX
    Explanations

    default settings, work, story

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

    The neuron activates on numeric literals in code.

    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
     aulas
    -0.97
    шое
    -0.95
    懋
    -0.95
    +++
    -0.93
    unction
    -0.93
     if
    -0.92
    пів
    -0.92
    CartItem
    -0.91
    хотво
    -0.90
     during
    -0.90
    POSITIVE LOGITS
    TINGS
    1.07
     ничего
    0.98
     dergleichen
    0.94
     Люди
    0.93
     nástro
    0.93
    芻
    0.93
     düşük
    0.92
     Сейчас
    0.91
     nimic
    0.91
    Nguy
    0.91
    Activations Density 0.005%

    No Known Activations