© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11979
    Prev
    Next
    INDEX
    Explanations

    code punctuation and import

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

    The neuron strongly activates on numeric sequences (digits and decimal points), i.e. it detects numbers rather than words.

    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
     (‘
    1.76
     ('
    1.73
     ‘
    1.45
     '[
    1.38
     ['
    1.38
     '
    1.34
    、『
    1.30
    ('
    1.18
    =('
    1.18
    ='/
    1.17
    POSITIVE LOGITS
    “
    0.90
    "$
    0.89
    "%
    0.88
     "%
    0.85
     "
    0.84
     "_
    0.81
    “”
    0.79
     "-
    0.78
     "".
    0.78
    "
    0.78
    Activations Density 0.034%

    No Known Activations