© 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. 10-GEMMASCOPE-RES-131K
    7. 57545
    Prev
    Next
    INDEX
    Explanations

    listing examples

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

    This neuron detects demonstrative reference words (e.g. that, these, those) and similar relational markers introducing examples or relationships.

    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
    を書
    -2.08
    咝
    -2.02
    孓
    -1.95
    mlung
    -1.93
     felpa
    -1.91
    】【
    -1.91
    翾
    -1.91
    旰
    -1.90
    );
    -1.90
    
    -1.87
    POSITIVE LOGITS
    st
    2.34
    “
    2.27
     â
    2.16
    ↵
    2.13
     \"
    1.95
    u
    1.92
    ,“
    1.90
    â
    1.88
     なく
    1.75
     \
    1.73
    Activations Density 0.030%

    No Known Activations