© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8430
    Prev
    Next
    INDEX
    Explanations

    two hot topics, two more

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

    The neuron strongly activates on the very first word of a new text segment (e.g. at the start of a paragraph or after a blank line).

    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_24_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
     compresses
    0.70
    所谓的
    0.69
     milled
    0.69
     groaned
    0.69
     remedied
    0.68
    Boost
    0.68
     이러
    0.68
     réduit
    0.67
    भाजपा
    0.66
    8
    0.65
    POSITIVE LOGITS
     ਤ
    0.98
    ANG
    0.89
    ным
    0.86
     необходимые
    0.86
    sächlich
    0.82
     மற்ற
    0.81
     batting
    0.81
    PAAm
    0.80
     строение
    0.80
    fromString
    0.79
    Activations Density 0.000%

    No Known Activations