© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    not applicable

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

    The neuron strongly activates on numeric literals (decimal or hex) appearing 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
    استان
    -1.16
    Už
    -1.14
    อาหาร
    -1.10
    ญี่ป
    -1.09
    Kepala
    -1.09
    そして
    -1.08
    平常
    -1.05
    ６
    -1.04
     skupina
    -1.04
    ühner
    -1.04
    POSITIVE LOGITS
     not
    1.47
     herum
    1.01
     today
    1.00
    )}-\
    0.99
     שלא
    0.98
    wark
    0.97
     sede
    0.96
     slapping
    0.96
    惟
    0.93
     what
    0.93
    Activations Density 0.001%

    No Known Activations