© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54155
    Prev
    Next
    INDEX
    Explanations

    microsoft, adobe, amazon, apple products

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

    The neuron is triggered by mentions of major software or tech‐product brand names.

    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
    は
    -1.88
    を
    -1.66
     are
    -1.47
    5
    -1.41
    ariConfig
    -1.40
    
    -1.37
    3
    -1.35
     появится
    -1.35
    ="
    -1.34
    lccccc
    -1.34
    POSITIVE LOGITS
    着脸
    1.37
     etui
    1.33
    ?»
    1.26
    …»
    1.23
    »?
    1.23
    `;
    
    1.23
    malıdır
    1.22
    為に
    1.21
    ものである
    1.21
    »)
    1.21
    Activations Density 0.121%

    No Known Activations