© 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. 107682
    Prev
    Next
    INDEX
    Explanations

    start of a descriptive phrase

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

    The neuron is keyed to tokens in formal report or policy document titles (e.g. the multi‐year “National Maternity Strategy for Ireland 2016–2022 ‘Creating a better future together’”).

    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
     drastic
    -0.95
     nötig
    -0.84
     Bø
    -0.84
     Besides
    -0.83
     উপ
    -0.81
     plenty
    -0.79
    EdgeInsets
    -0.79
     classy
    -0.79
    璟
    -0.79
    izability
    -0.77
    POSITIVE LOGITS
    וּ
    0.98
    ogia
    0.91
    ᅲ
    0.90
    tidase
    0.88
    ִּ
    0.85
     wedded
    0.81
     reput
    0.81
     мне
    0.80
     věci
    0.80
    ּוֹ
    0.80
    Activations Density 0.011%

    No Known Activations