© 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. 22-GEMMASCOPE-RES-131K
    7. 40303
    Prev
    Next
    INDEX
    Explanations

    words ending in able or ible

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

    The neuron detects the stems of long, uncommon polysyllabic (often Latinate) words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.79
     in
    -1.79
    嗚
    -1.66
     during
    -1.64
    もあるので
    -1.56
    ترة
    -1.53
     since
    -1.52
    춰
    -1.52
    今後
    -1.51
     after
    -1.46
    POSITIVE LOGITS
     erklärt
    1.59
    ↵↵
    1.59
     ambassade
    1.56
    ى
    1.55
    ate
    1.49
    昨天
    1.49
     seinem
    1.48
    ly
    1.48
    為に
    1.45
     toalha
    1.45
    Activations Density 0.063%

    No Known Activations