© 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. 70465
    Prev
    Next
    INDEX
    Explanations

    proper names and technical terms

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

    The neuron responds to longer, uncommon tokens—especially technical‐oriented terms and proper names—i.e. specialized jargon or proper nouns.

    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
    ㈯
    -2.59
    ↑↑↑
    -2.47
    ！"
    -2.44
    ✔
    -2.44
    蒟
    -2.42
    Ꮏ
    -2.41
    ↓↓
    -2.39
     Juegos
    -2.38
    ▪️
    -2.31
    蕯
    -2.31
    POSITIVE LOGITS
    .
    2.91
    the
    2.67
    O
    2.59
     业
    2.44
     grossen
    2.42
     THREE
    2.41
    </h4>
    2.39
    沨
    2.38
    晝
    2.38
     entsprechenden
    2.36
    Activations Density 0.002%

    No Known Activations