© 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. 10245
    Prev
    Next
    INDEX
    Explanations

    lineage cells

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

    The neuron detects the word "lineage" in scientific contexts, particularly related to cell biology and stem cell research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specifically fires on the term “lineage,” i.e. references to biological lineages or cell-line classifications.

    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
    0
    -2.41
    怱
    -2.39
    hamilan
    -2.30
    ཋ
    -2.30
     ';
    
    -2.25
    各样的
    -2.23
    耵
    -2.19
    鉏
    -2.19
    鐿
    -2.19
    倥
    -2.19
    POSITIVE LOGITS
     Their
    2.81
    賔
    2.72
    D
    2.58
    h
    2.55
    谖
    2.33
    quot
    2.30
    的
    2.30
     establece
    2.27
     brutality
    2.19
     команда
    2.19
    Activations Density 0.002%

    No Known Activations