© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    France flag 🇫

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

    The neuron detects non‐lexical, formatting or layout tokens—e.g. unusual spaces, punctuation marks, markdown symbols, and emojis.

    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
     b
    -0.91
     m
    -0.90
     grand
    -0.84
     varias
    -0.84
     plan
    -0.84
     к
    -0.84
     so
    -0.81
     region
    -0.79
     refer
    -0.76
     died
    -0.76
    POSITIVE LOGITS
     👍
    1.13
    ﺅ
    0.98
     fondateur
    0.95
    jooq
    0.91
     sourire
    0.90
     estrenar
    0.90
    ቄ
    0.90
     😊
    0.89
     koste
    0.89
    उत्तर
    0.88
    Activations Density 0.043%

    No Known Activations