© 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. 75154
    Prev
    Next
    INDEX
    Explanations

    names ending in iti, ine, or idin

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

    The neuron activates strongly on tokens that are proper names (people or places), i.e. named-entity tokens.

    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
    噲
    -1.98
    ꯸
    -1.93
    耵
    -1.92
    很喜欢
    -1.91
    是一個
    -1.91
    		
    -1.90
    ︲
    -1.88
    凩
    -1.88
    是很
    -1.87
    髕
    -1.85
    POSITIVE LOGITS
     this
    1.92
     Although
    1.84
     After
    1.84
    ),
    1.84
     While
    1.82
    <td>
    1.78
     During
    1.77
    *{\
    1.71
     exquisite
    1.67
    ка
    1.65
    Activations Density 0.004%

    No Known Activations