© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10406
    Prev
    Next
    INDEX
    Explanations

    un- words

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

    This neuron detects the negative prefix “un-” (especially when hyphenated) attached to words.

    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
     häufig
    -2.20
     begle
    -2.02
    In
    -2.02
    昼食
    -2.00
    あっという
    -1.99
     vorbere
    -1.98
     fehler
    -1.98
     two
    -1.89
    僅
    -1.85
    现在的
    -1.84
    POSITIVE LOGITS
    孭
    1.80
     "
    1.77
     investi
    1.74
    🧌
    1.73
    ’?
    1.73
    𝐆
    1.68
    ꈊ
    1.65
     uſed
    1.64
     voi
    1.63
    iz
    1.60
    Activations Density 0.004%

    No Known Activations