© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5673
    Prev
    Next
    INDEX
    Explanations

    RJ, Buj, Moj, FJ, aji, raj, ji, conj

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

    The neuron fires on named‐entity and other specialized content tokens—things like people’s or company names, technical terms, or similar uncommon proper nouns.

    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
    uose
    0.60
    perti
    0.57
    oq
    0.57
    ادم
    0.56
    }",
    0.56
     நாடு
    0.54
    ింది
    0.54
    balo
    0.54
     libsql
    0.53
    েইন
    0.53
    POSITIVE LOGITS
    unctive
    0.88
    ्ज
    0.84
    ्ञ
    0.80
    ્ઞ
    0.70
    ｬ
    0.70
    丷
    0.69
    AX
    0.66
    uncture
    0.66
    unct
    0.66
    äger
    0.66
    Activations Density 0.294%

    No Known Activations