© 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. 84541
    Prev
    Next
    INDEX
    Explanations

    art and exhibitions

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

    The neuron fires on title‐ or heading‐style tokens (proper names, exhibition titles, and other capitalized/content‐bearing words in section headers).

    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
    kette
    -1.04
     일반
    -0.84
     hermosas
    -0.81
    モニ
    -0.81
    akterysty
    -0.78
     پخش
    -0.77
     Mermaid
    -0.77
    createDate
    -0.77
    msub
    -0.76
     OLS
    -0.76
    POSITIVE LOGITS
    Objects
    1.09
     objects
    1.05
     Objekte
    0.99
     Sammlung
    0.93
     connections
    0.93
    цать
    0.92
     альбом
    0.91
    ставка
    0.91
    rafts
    0.89
    fluence
    0.85
    Activations Density 0.027%

    No Known Activations