© 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. 36489
    Prev
    Next
    INDEX
    Explanations

    criminated, control, circuit

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

    The neuron responds to common English word‐ending morphemes—especially suffixes like –ing, –ed, and –ion.

    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
    这
    -1.17
    /";
    -1.09
     interesses
    -1.09
    こんな
    -1.07
    这个
    -1.07
    お値段
    -1.07
     kursi
    -1.06
     aktivi
    -1.06
    がこの
    -1.05
    iciar
    -1.04
    POSITIVE LOGITS
     Gnade
    1.06
    喰
    1.05
    
    1.00
     xD
    1.00
    种植
    0.99
    水が
    0.99
     выхода
    0.97
     மற்ற
    0.96
     läsa
    0.96
     th
    0.95
    Activations Density 0.003%

    No Known Activations