© 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. 22-GEMMASCOPE-RES-131K
    7. 14144
    Prev
    Next
    INDEX
    Explanations

    recent or today

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

    The neuron strongly activates on self-referential, first-person narration (e.g. “I,” “my,” “here’s”) in personal posts.

    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
     ANDREW
    -1.22
     SEVENTH
    -1.14
    ʹ
    -1.14
    ⇕
    -1.09
    ________,
    -1.08
    -;
    -1.08
     pfe
    -1.06
    っちゃった
    -1.05
     alojamientos
    -1.05
    thousands
    -1.05
    POSITIVE LOGITS
     recently
    1.75
     немного
    1.54
    最近
    1.41
     recent
    1.34
     lately
    1.34
    Če
    1.27
    简单
    1.27
     yesterday
    1.26
     today
    1.25
     Recently
    1.23
    Activations Density 0.071%

    No Known Activations