© 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. 87264
    Prev
    Next
    INDEX
    Explanations

    making things

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

    The neuron fires strongly on first‐person descriptions of constructing or building something (e.g. “I built…,” “using…,” “made…,” “built…,” 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
    ography
    -1.27
    isait
    -1.26
    ability
    -1.24
    alties
    -1.21
    givings
    -1.20
    
    -1.20
    ification
    -1.18
    ier
    -1.17
    ueroa
    -1.16
    itis
    -1.16
    POSITIVE LOGITS
     επίσης
    1.27
    gili
    1.25
     recaudación
    1.24
    PARATUS
    1.19
     cerámica
    1.17
     χρησιμοποι
    1.16
     cafetería
    1.13
     would
    1.10
    bater
    1.10
     his
    1.08
    Activations Density 0.114%

    No Known Activations