© 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. 22-GEMMASCOPE-RES-131K
    4. 39857
    Prev
    Next
    INDEX
    Explanations

    submission status dates

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

    The neuron detects date‐stamp metadata in academic paper headers (e.g. “Received …,” “Accepted …”).

    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
     of
    -1.58
    Of
    -1.14
    ोजन
    -1.04
    Any
    -1.04
    if
    -1.03
     sadar
    -0.99
    哧
    -0.97
    AccessFile
    -0.95
    就没
    -0.95
    Stderr
    -0.94
    POSITIVE LOGITS
     submitted
    1.30
     Accepted
    1.27
    🦽
    1.06
     submission
    1.04
     submissions
    1.03
    提交
    1.03
    quiti
    1.03
    рення
    1.02
     sentada
    1.00
     llenos
    1.00
    Activations Density 0.049%

    No Known Activations