© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76658
    Prev
    Next
    INDEX
    Explanations

    without a doubt

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

    The neuron fires on occurrences of the word “without,” especially in discourse-linking phrases.

    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
    ╵
    -0.79
    Spesifikasi
    -0.78
    lı
    -0.77
    forEach
    -0.75
    Пусть
    -0.75
     একটি
    -0.73
    ۣ
    -0.73
    ının
    -0.73
    ệu
    -0.73
    が
    -0.73
    POSITIVE LOGITS
     doubt
    5.25
    doubt
    3.33
     Doubt
    2.98
    Doubt
    2.77
     question
    2.58
     dúvida
    2.42
     dubbio
    2.42
     doute
    2.41
     doubted
    2.28
     duda
    2.27
    Activations Density 0.013%

    No Known Activations