© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86902
    Prev
    Next
    INDEX
    Explanations

    feeds and specific content types

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

    The neuron fires on mentions of RSS/feed parsing—e.g. the feedparser module, parse calls, or RSS feed URLs.

    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
    ༽
    -0.98
     afectada
    -0.80
     conhecida
    -0.79
     mine
    -0.76
    Ведущий
    -0.74
     verdadero
    -0.73
    iální
    -0.71
     веду
    -0.71
     resistencia
    -0.71
    Adverten
    -0.70
    POSITIVE LOGITS
    Feed
    0.86
    FEED
    0.84
    Survivors
    0.82
    pædia
    0.80
    彿
    0.79
    끔
    0.78
     valde
    0.75
     Feed
    0.75
    𝐀
    0.75
    军
    0.75
    Activations Density 0.008%

    No Known Activations