© 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. 10-GEMMASCOPE-RES-131K
    7. 66081
    Prev
    Next
    INDEX
    Explanations

    AFP news agency

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

    The neuron detects AFP news‐agency credit tokens (e.g. “AFP” in photo or byline credits).

    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
    沨
    -2.72
    枞
    -2.59
    辚
    -2.52
    鲀
    -2.50
    皛
    -2.48
     maar
    -2.34
    ЭС
    -2.30
    ⸎
    -2.28
    潆
    -2.25
     così
    -2.22
    POSITIVE LOGITS
    ?”
    2.98
    秶
    2.63
    薷
    2.61
    わたしは
    2.42
     bestellt
    2.25
    廰
    2.20
     vorigen
    2.16
     magnético
    2.13
    is
    2.05
     overcomes
    2.05
    Activations Density 0.003%

    No Known Activations