© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84566
    Prev
    Next
    INDEX
    Explanations

    practice

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

    This neuron fires on the opening “X is …” definitional/topic‐introduction sentences that present a term and its definition.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᆨ
    -0.72
    嗪
    -0.72
    ↗
    -0.70
    隊長
    -0.68
     arbets
    -0.68
     acting
    -0.67
    Ȃ
    -0.67
     felhasznál
    -0.66
     einfache
    -0.66
     bekerja
    -0.65
    POSITIVE LOGITS
     practice
    4.41
     practiced
    4.25
    practi
    4.09
     practicing
    3.92
    practice
    3.80
    Practi
    3.80
     practised
    3.66
     practise
    3.52
     practising
    3.45
     Practi
    3.42
    Activations Density 0.113%

    No Known Activations