© 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. 48148
    Prev
    Next
    INDEX
    Explanations

    storm drains and Wnt signaling

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

    water-related terms including rainwater, storms, drainage systems, and precipitation.

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

    The neuron activates on numeric measurements and quantities (numbers, often with decimals).

    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
    </em>
    -1.88
    ୈ
    -1.72
    翾
    -1.57
    ).
    -1.55
    although
    -1.51
     expose
    -1.49
     lelaki
    -1.46
    вана
    -1.41
    shall
    -1.41
     exploit
    -1.39
    POSITIVE LOGITS
     divertida
    1.66
     rempli
    1.56
     maravillosa
    1.52
     représenté
    1.50
    Ꮛ
    1.48
    いたしました
    1.47
    蟶
    1.47
     cremallera
    1.47
     erklär
    1.44
     geschehen
    1.44
    Activations Density 0.028%

    No Known Activations