© 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. 22-GEMMASCOPE-RES-131K
    7. 40013
    Prev
    Next
    INDEX
    Explanations

    figure labels and descriptions

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

    The neuron flags document headings that introduce numbered elements (e.g. “Figure 1: …” or “Table 17.”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    乜
    -1.09
    Ранее
    -1.09
     nomadic
    -1.05
    -```
    -1.05
    我不知道
    -1.00
     следующих
    -1.00
    Эти
    -0.98
    Напомним
    -0.98
     ilustracji
    -0.97
     penyer
    -0.96
    POSITIVE LOGITS
     worldwide
    1.23
     garcía
    1.13
     countries
    1.09
     rodríguez
    1.05
     showing
    1.02
     view
    1.02
     dejamos
    1.02
     joão
    1.00
     móvel
    0.99
    .
    0.97
    Activations Density 0.004%

    No Known Activations