© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    family and context

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

    The neuron detects mentions of “family” (references to a person’s family).

    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
     fifteen
    -1.73
     thirteen
    -1.66
     Trying
    -1.59
     three
    -1.59
     Eight
    -1.55
     Through
    -1.53
     seven
    -1.52
     if
    -1.52
     sixteen
    -1.52
    Also
    -1.51
    POSITIVE LOGITS
     
    1.58
     รวม
    1.56
    峮
    1.52
     lmao
    1.49
     การ
    1.48
     passando
    1.40
     ihe
    1.37
    衚
    1.37
     бизнес
    1.37
     famoso
    1.37
    Activations Density 0.012%

    No Known Activations