© 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. 22-GEMMASCOPE-RES-131K
    7. 39898
    Prev
    Next
    INDEX
    Explanations

    this kind of

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

    The neuron activates on the demonstrative pronouns “this” and “these.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    為に
    -2.42
    すっ
    -2.25
    久し
    -2.16
    あー
    -2.05
    えっ
    -1.98
    ほら
    -1.87
    来週
    -1.87
    ようになって
    -1.87
    つづく
    -1.85
    ことも
    -1.83
    POSITIVE LOGITS
    <bos>
    1.96
     as
    1.67
    轍
    1.55
    <0xA3>
    1.52
     only
    1.51
     mainly
    1.49
     primarily
    1.46
    そのため
    1.46
     although
    1.46
     one
    1.46
    Activations Density 0.092%

    No Known Activations