© 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. 10-GEMMASCOPE-RES-131K
    4. 65613
    Prev
    Next
    INDEX
    Explanations

    arterioles, rightful ownership, proper nouns

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

    The neuron strongly flags domain-specific jargon and proper names, whether in code (e.g. “Botan,” “Synch”) or in biomedical terminology (e.g. “arterio,” “subarachnoid”).

    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
    );
    -2.88
     centaines
    -2.61
     dizaines
    -2.55
    ");
    
    -2.50
     hidupnya
    -2.47
    洐
    -2.41
    .
    -2.38
    })=
    -2.34
    毉
    -2.30
    Because
    -2.27
    POSITIVE LOGITS
    呖
    3.00
     hermanas
    2.83
    姽
    2.81
     verdades
    2.73
    臯
    2.72
    鋱
    2.69
     在
    2.58
    我
    2.55
    垍
    2.53
    
    2.52
    Activations Density 0.054%

    No Known Activations