© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45248
    Prev
    Next
    INDEX
    Explanations

    dos and don'ts

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

    The neuron activates specifically on the lowercase token “dos.”

    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
    0
    -3.05
    神
    -2.75
    вгений
    -2.58
    啬
    -2.56
    Ꮉ
    -2.53
    夲
    -2.50
    撄
    -2.50
    欵
    -2.45
    彞
    -2.44
     vårt
    -2.38
    POSITIVE LOGITS
     dos
    2.52
     However
    2.42
    国外
    2.41
    琹
    2.39
     Attending
    2.36
    缡
    2.33
    存知
    2.33
     exacting
    2.30
    ⊲
    2.27
    s
    2.25
    Activations Density 0.003%

    No Known Activations