© 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. 75118
    Prev
    Next
    INDEX
    Explanations

    Hampton, hippocampal, MacBook

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

    The neuron is specialized to detect the proper name “Hampton” (i.e. occurrences of the token “Hampton”).

    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
    歘
    -2.97
    肏
    -2.66
    ⸫
    -2.66
     所以
    -2.63
    垰
    -2.61
     Gefühle
    -2.59
    mpagne
    -2.58
     fortfarande
    -2.55
    されてる
    -2.55
    鰨
    -2.53
    POSITIVE LOGITS
    ’
    3.00
    i
    3.00
    </td>
    2.58
    趼
    2.56
    these
    2.44
    䉴
    2.34
    鿬
    2.34
     οποίο
    2.33
       
    2.31
    ated
    2.31
    Activations Density 0.002%

    No Known Activations