© 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. 29052
    Prev
    Next
    INDEX
    Explanations

    friends and family

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

    This neuron detects occurrences of the substring “friend” (e.g. “friends,” “girlfriend,” “best friends”).

    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
    ↵
    -1.93
    </em>
    -1.92
     they
    -1.59
    ÓN
    -1.59
    Innovation
    -1.45
    嫫
    -1.42
    
    -1.42
    緜
    -1.41
    unuz
    -1.38
    tığı
    -1.38
    POSITIVE LOGITS
     {
    
    2.06
    colta
    1.80
     그는
    1.73
    mbgg
    1.73
     Seleccione
    1.71
    阋
    1.70
     دخترانه
    1.70
    却不
    1.64
     涂
    1.62
    嚓
    1.62
    Activations Density 0.038%

    No Known Activations