© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8937
    Prev
    Next
    INDEX
    Explanations

    en followed by specific words

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

    The neuron selectively activates on tokens beginning with the letter sequence “En” (e.g. Encomium, Enforced, Enrique).

    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
    ريم
    0.65
    adjoint
    0.55
    ersonic
    0.55
    ními
    0.54
    lden
    0.53
    ர்வ
    0.52
    bereit
    0.52
    猬
    0.52
     ہ
    0.52
     عامل
    0.52
    POSITIVE LOGITS
    En
    1.01
     En
    0.98
     enk
    0.79
     passant
    0.75
     EN
    0.73
     Enzo
    0.73
     enl
    0.71
     en
    0.71
     Enrico
    0.71
     Enrich
    0.70
    Activations Density 0.168%

    No Known Activations