© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42379
    Prev
    Next
    INDEX
    Explanations

    addresses to leaders

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

    The neuron fires on bits of formal “front‐matter” in text—greetings, salutations, addresses to a chair or president, and other meeting‐ or speech‐opening 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_10/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
    idikan
    -1.45
    彼の
    -1.41
    Etimología
    -1.38
     ezzel
    -1.37
    romi
    -1.28
     pandémie
    -1.27
     menggelar
    -1.24
    EME
    -1.24
    CLUYE
    -1.21
     lots
    -1.20
    POSITIVE LOGITS
    ↵
    1.41
    omaly
    1.31
     then
    1.31
     администрации
    1.28
    使用
    1.27
     residence
    1.23
     تفاوت
    1.22
    İyi
    1.22
     aguj
    1.21
    akterysty
    1.20
    Activations Density 0.026%

    No Known Activations