© 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. 79825
    Prev
    Next
    INDEX
    Explanations

    Self-management, long-term durations, unfinished states

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

    The neuron fires whenever it sees the XML/TMX attribute “unfinished” (i.e. markers of an incomplete or pending translation).

    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
    bàn
    -0.94
    Aggregation
    -0.90
     quai
    -0.89
    鹗
    -0.88
    ISMS
    -0.88
     quinze
    -0.87
    NoError
    -0.86
     её
    -0.86
    ヨーク
    -0.86
     sourire
    -0.85
    POSITIVE LOGITS
    5
    1.06
    8
    1.05
     if
    1.05
    3
    1.02
    6
    0.96
     basically
    0.95
     illustrazione
    0.92
    了一遍
    0.90
    7
    0.90
     during
    0.88
    Activations Density 0.000%

    No Known Activations