© 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. 13991
    Prev
    Next
    INDEX
    Explanations

    Key improvements and explanations:

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

    The neuron strongly activates on numeric literal tokens—especially floating‐point numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ANCH
    0.55
    shtml
    0.53
    ]",
    0.52
    ië
    0.52
    ombie
    0.51
     TOUCH
    0.50
    iquest
    0.49
     அஜித்
    0.49
    Tunes
    0.49
    чатку
    0.48
    POSITIVE LOGITS
     pyridine
    0.59
     đường
    0.55
     fluoride
    0.55
     adsorbent
    0.55
    まる
    0.55
    <code>
    0.52
    何か
    0.52
     crecimiento
    0.51
    ચારી
    0.51
    படுத்த
    0.50
    Activations Density 0.003%

    No Known Activations