© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    mathematical primes

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

    The neuron fires on structural or metadata tokens—things like section headings, labels or attribute names, link prompts (e.g. “Read more:”), and similar document‐format markers.

    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
    ناك
    0.54
    }}}\
    0.52
     }\
    0.51
     područ
    0.51
    ohia
    0.50
     Posteriormente
    0.50
     posteriorly
    0.50
    }}}}$
    0.50
    ógy
    0.49
    डला
    0.49
    POSITIVE LOGITS
    тки
    0.52
     arbitrator
    0.51
    :</
    0.49
    ರಿ
    0.49
    ?</
    0.49
    abt
    0.48
    Virt
    0.48
    рма
    0.48
    フィール
    0.48
     unresolved
    0.47
    Activations Density 0.027%

    No Known Activations