© 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. 119025
    Prev
    Next
    INDEX
    Explanations

    Indian names and places

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

    The neuron fires strongly on capitalized proper nouns (named entities).

    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
    </h1>
    -1.95
     ridu
    -1.71
     speciali
    -1.68
     territoires
    -1.66
     '';
    
    -1.65
     brillant
    -1.59
    膂
    -1.59
    鑁
    -1.59
     appla
    -1.59
     llu
    -1.55
    POSITIVE LOGITS
    (
    2.42
    </em>
    2.30
    *
    1.99
    It
    1.86
    The
    1.77
     promesas
    1.74
    </sup>
    1.74
     to
    1.68
     desnuda
    1.68
     virtudes
    1.67
    Activations Density 0.052%

    No Known Activations