© 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. 68857
    Prev
    Next
    INDEX
    Explanations

    bewitched, befriend, and befitting

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

    The neuron strongly activates on words beginning with the prefix “be-.”

    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
    𓋼
    -2.53
    ли
    -2.52
    i
    -2.45
     supposed
    -2.31
    牁
    -2.23
     coment
    -2.09
    Ǎ
    -2.06
    N
    -1.98
     свое
    -1.96
     divides
    -1.96
    POSITIVE LOGITS
     But
    3.28
     They
    3.20
     However
    3.02
     Which
    2.69
     There
    2.63
    ...?
    2.28
     Again
    2.23
    sandalia
    2.22
    ⩤
    2.20
    上学
    2.19
    Activations Density 0.023%

    No Known Activations