© 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. 22-GEMMASCOPE-RES-131K
    7. 14241
    Prev
    Next
    INDEX
    Explanations

    program code and numbers

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

    The neuron consistently fires on numeric literals (whole numbers and decimals) in code or data.

    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
    obviously
    -1.19
    ſſen
    -1.16
    commonly
    -1.14
     tevé
    -1.14
    thousands
    -1.13
    whose
    -1.10
     considère
    -1.08
     rése
    -1.08
    sont
    -1.08
    matur
    -1.07
    POSITIVE LOGITS
     this
    1.10
    ↵↵↵↵↵↵↵↵↵
    1.07
     for
    1.05
     additional
    1.04
     one
    0.94
     even
    0.94
     provide
    0.92
     ....
    0.91
     holds
    0.91
     J
    0.91
    Activations Density 0.002%

    No Known Activations