© 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. 81246
    Prev
    Next
    INDEX
    Explanations

    haven't / hasn't

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

    The neuron is highly responsive to common personal pronouns (e.g. I, you, it, they).

    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
     damaligen
    -0.84
    되는
    -0.82
    cephala
    -0.82
    :"#
    -0.81
     unrelated
    -0.79
     Französ
    -0.78
     Zeugen
    -0.77
    誰でも
    -0.77
    後來
    -0.75
     religione
    -0.75
    POSITIVE LOGITS
     hasn
    6.88
     haven
    6.59
     hadn
    4.91
     havent
    3.84
    haven
    3.72
    Haven
    3.67
     belum
    3.45
     Haven
    3.38
     chưa
    3.22
    还没有
    2.75
    Activations Density 0.226%

    No Known Activations