© 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. 256
    Prev
    Next
    INDEX
    Explanations

    of followed by a noun or article

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

    The main thing this neuron does is detect occurrences of the word “life” (and its plural form “lives”).

    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
     preparada
    -1.26
     personalizado
    -1.24
    してた
    -1.23
     conseguido
    -1.23
    camisa
    -1.22
     elaborado
    -1.21
     henvis
    -1.20
     fundido
    -1.20
    だったが
    -1.20
     occasions
    -1.16
    POSITIVE LOGITS
     of
    1.56
     our
    1.46
    the
    1.36
     someone
    1.23
     gás
    1.22
     others
    1.21
     you
    1.20
    )=>{
    
    1.18
     pady
    1.18
    a
    1.16
    Activations Density 0.070%

    No Known Activations