© 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. 61028
    Prev
    Next
    INDEX
    Explanations

    idea for this

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

    This neuron activates on the word “idea” (and its plural “ideas”), flagging explicit mentions of ideas or suggestions.

    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
    ↵
    -1.98
    with
    -1.63
    where
    -1.63
    Kommentare
    -1.59
     gdzie
    -1.55
    between
    -1.51
    豋
    -1.46
    焌
    -1.45
     який
    -1.44
     upang
    -1.43
    POSITIVE LOGITS
     ideas
    2.52
     about
    2.39
     Idea
    1.95
     idea
    1.83
    .
    1.81
    ideas
    1.61
     IDEA
    1.57
     others
    1.52
     Ideas
    1.49
    ếng
    1.48
    Activations Density 0.044%

    No Known Activations