© 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. 12534
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron fires strongly on plural, countable nouns (words that denote collections or sets).

    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
    ListIterator
    0.63
    ijj
    0.57
    engkapi
    0.55
    ijnen
    0.54
    igsaw
    0.54
    (([
    0.53
     विनय
    0.53
    יין
    0.52
    دى
    0.52
    صوص
    0.52
    POSITIVE LOGITS
     xwe
    0.54
     Oso
    0.53
     Umesh
    0.53
     Walgreens
    0.52
     Qd
    0.51
     APO
    0.50
     Apo
    0.50
     Sprache
    0.50
     Prisma
    0.50
     用
    0.50
    Activations Density 0.009%

    No Known Activations