© 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. 10-GEMMASCOPE-RES-131K
    4. 130441
    Prev
    Next
    INDEX
    Explanations

    job candidate opportunity

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

    This neuron fires on the structural markers of bulleted or enumerated job‐description lists—e.g. the leading dashes, section headings like “Skills and Requirements:,” and the numbers (years of experience, item numbers) that mark individual list items.

    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
    :“……”
    -1.66
     estrena
    -1.65
     reúne
    -1.59
    を購入
    -1.55
    hedrals
    -1.50
     totiž
    -1.48
     nació
    -1.48
    Irlande
    -1.46
     anuncia
    -1.42
    一愣
    -1.41
    POSITIVE LOGITS
     or
    1.61
    .
    1.55
    🤎
    1.51
    靱
    1.45
    datable
    1.45
                        
    1.44
                
    1.43
    🤠
    1.43
    				
    1.41
    =\"
    1.41
    Activations Density 0.174%

    No Known Activations