© 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. 33554
    Prev
    Next
    INDEX
    Explanations

    brothers

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

    The neuron flags unusually salient or content‐bearing tokens—especially proper names, dates, and other rare or “high‐information” words.

    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
    あえず
    -1.00
     schreef
    -0.88
    corbic
    -0.85
    olut
    -0.81
    🏋
    -0.79
     strlen
    -0.77
    дає
    -0.77
     Prophet
    -0.75
     consummate
    -0.74
     schrijven
    -0.73
    POSITIVE LOGITS
     brothers
    1.12
     Brothers
    1.01
    brothers
    0.88
     brethren
    0.85
    Brothers
    0.82
     BROTHERS
    0.82
     brother
    0.81
     Kingdom
    0.79
    brother
    0.78
     comment
    0.76
    Activations Density 0.004%

    No Known Activations