© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7595
    Prev
    Next
    INDEX
    Explanations

    when describing a condition

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

    The neuron strongly detects occurrences of the conjunction “When,” especially at the start of a new sentence or clause.

    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_24_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
    f
    1.40
    ação
    1.30
    v
    1.27
    в
    1.27
    ból
    1.24
    c
    1.23
     মজুমদার
    1.16
    idagi
    1.15
    هاي
    1.15
    dzi
    1.14
    POSITIVE LOGITS
    soever
    2.02
     xưa
    1.37
    마다
    1.30
     adduct
    1.22
    쯤
    1.20
    事人
    1.12
    ी
    1.09
    hydroxyl
    1.06
     وعند
    1.05
    numbered
    1.02
    Activations Density 0.078%

    No Known Activations