© 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. 11914
    Prev
    Next
    INDEX
    Explanations

    word and words

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

    The neuron primarily looks for terms related to word‐study and language learning—e.g. vocabulary, pronunciation, dictionaries, definitions, and related educational materials.

    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
    🏌
    0.56
     подразуме
    0.54
     형식
    0.52
     histori
    0.51
     হুমকি
    0.51
     территория
    0.51
     تهد
    0.51
    summary
    0.50
     GUIContent
    0.50
     читать
    0.50
    POSITIVE LOGITS
    词
    1.75
    Word
    1.71
     word
    1.70
    word
    1.66
     Word
    1.66
     Words
    1.66
     words
    1.63
     WORDS
    1.60
     WORD
    1.59
    Words
    1.55
    Activations Density 0.171%

    No Known Activations