© 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. 10-GEMMASCOPE-RES-131K
    7. 69113
    Prev
    Next
    INDEX
    Explanations

    "out of" + reason

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

    The neuron is triggered by the phrase “out of” when it appears with numeric values (as in “out of 197,” “out of 188,” etc.), i.e. ratios or counts expressed as “out of <number>.”

    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
    ть
    -1.55
    塒
    -1.46
     {'
    -1.45
     как
    -1.44
     做
    -1.38
    примеча
    -1.38
     存
    -1.36
    謦
    -1.34
    Ґ
    -1.34
    quise
    -1.34
    POSITIVE LOGITS
     případ
    1.95
    ların
    1.94
    本当は
    1.56
     “
    1.54
    也得
    1.52
    担心
    1.52
    
    1.48
    Potencia
    1.48
    empresas
    1.45
     الرغم
    1.44
    Activations Density 0.011%

    No Known Activations