© 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. 13858
    Prev
    Next
    INDEX
    Explanations

    unchanged or same

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

    The neuron is keyed to relatively rare, multi-syllable content words (i.e. technical or topic-specific vocabulary) rather than common function words.

    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
    ૯
    0.55
     еще
    0.54
    ͡
    0.52
    ୮
    0.52
     Еще
    0.51
    ϋ
    0.50
     మరి
    0.50
    ције
    0.49
    亥
    0.49
     anonymously
    0.48
    POSITIVE LOGITS
     unchanged
    2.98
    不变
    2.56
    保持
    2.48
     remained
    2.45
     그대로
    2.45
     remain
    2.42
     retained
    2.41
     unaltered
    2.39
     retain
    2.34
     retains
    2.34
    Activations Density 0.884%

    No Known Activations