© 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. 85268
    Prev
    Next
    INDEX
    Explanations

    familiarity and acquaintance

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

    The neuron detects expressions that mean becoming familiar with or getting to know something.

    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
    ),
    -1.62
    _{
    -1.55
      
    -1.54
     "
    -1.51
    震撼
    -1.47
    )$
    -1.42
    tt
    -1.42
    ^{
    -1.42
    ではなく
    -1.41
     оно
    -1.40
    POSITIVE LOGITS
     firsthand
    1.84
    蹓
    1.75
     kazak
    1.74
     barbati
    1.70
    袿
    1.65
    沨
    1.63
    𝔗
    1.62
     traduce
    1.60
    introduce
    1.58
     perfecte
    1.57
    Activations Density 0.009%

    No Known Activations