© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83811
    Prev
    Next
    INDEX
    Explanations

    unique, well, and inspired descriptions

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

    The neuron flags evaluative, descriptive review language—especially praise or ranking phrases (e.g. “17th book in 20 years,” “well-worked novel,” “southern rock,” “unique sound”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⁠
    -1.19
     ✨
    -1.18
    elsey
    -1.16
    🪛
    -1.16
     instagram
    -1.13
    rasti
    -1.13
    formazioni
    -1.12
    й
    -1.09
    🫓
    -1.07
     aesthetics
    -1.06
    POSITIVE LOGITS
     реально
    1.05
     yng
    0.96
     heretofore
    0.95
     läßt
    0.95
     sez
    0.92
     parfum
    0.91
    IMHO
    0.90
     skall
    0.89
     sés
    0.88
     parla
    0.88
    Activations Density 0.089%

    No Known Activations