© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44309
    Prev
    Next
    INDEX
    Explanations

    defines and describes entities

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

    The neuron detects the definitional “is a” pattern used in article lead sentences (e.g. “The X is a Y…”).

    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
     with
    -1.82
    zzet
    -1.42
    saia
    -1.40
    mavi
    -1.40
     and
    -1.40
    他の
    -1.38
    mogen
    -1.37
    pezifische
    -1.27
    sams
    -1.27
    istanbul
    -1.26
    POSITIVE LOGITS
     if
    2.08
    ↵↵↵
    1.69
    if
    1.42
    ↵↵↵↵↵
    1.39
    ↵↵↵↵
    1.39
     of
    1.35
     If
    1.30
     furia
    1.28
     jika
    1.27
     ;
    
    1.25
    Activations Density 0.243%

    No Known Activations