© 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. 99635
    Prev
    Next
    INDEX
    Explanations

    related topics

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

    The neuron detects section headings beginning with the word “Related” (e.g. “Related Events,” “Related Reviews,” “Related Media,” etc.).

    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
     memperbaiki
    -1.55
    èlement
    -1.55
    ibouti
    -1.52
    entemente
    -1.48
    heses
    -1.43
    krank
    -1.41
    agoza
    -1.41
    issement
    -1.40
    isateurs
    -1.38
     membersihkan
    -1.37
    POSITIVE LOGITS
     related
    2.00
    related
    1.82
     Related
    1.63
     assures
    1.63
    似的
    1.56
     feuer
    1.49
     resembles
    1.48
    
    1.47
     rosario
    1.45
     giu
    1.44
    Activations Density 0.108%

    No Known Activations