© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5275
    Prev
    Next
    INDEX
    Explanations

    formatting strings with curly braces

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

    The neuron primarily detects numeric literals (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    داً
    0.58
    }"/>
    0.57
    ]");
    0.55
     knee
    0.54
     enda
    0.54
    هرة
    0.54
     Knee
    0.54
    ologo
    0.53
    Layers
    0.52
     luchar
    0.52
    POSITIVE LOGITS
    }'.
    1.20
     {}'.
    1.19
    {}'.
    1.13
    '.
    0.97
    """.
    0.88
     '.
    0.85
     "".
    0.84
    :'.
    0.84
    ''.
    0.83
    ='.
    0.82
    Activations Density 0.008%

    No Known Activations