© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39410
    Prev
    Next
    INDEX
    Explanations

    if so, how

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

    This neuron detects the conditional follow-up phrase “If so,” (an “If” immediately followed by “so,”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     you
    -1.61
     your
    -1.54
    ]]]
    -1.44
     =>'
    -1.43
     politika
    -1.41
    你别
    -1.40
     aforementioned
    -1.40
     حتی
    -1.38
     perilous
    -1.38
     você
    -1.38
    POSITIVE LOGITS
     then
    1.47
    これは
    1.42
    苼
    1.39
    אח
    1.38
     hins
    1.36
    这
    1.32
    œuf
    1.31
    乆
    1.30
    ไป
    1.30
     become
    1.27
    Activations Density 0.048%

    No Known Activations