© 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. 21843
    Prev
    Next
    INDEX
    Explanations

    technical, informal, and named entities

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

    The neuron detects tokens that start with a capital letter (proper nouns, class/annotation names, or other uppercase identifiers).

    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
     multitude
    -2.53
    𓄹
    -2.52
     immerse
    -2.31
    槩
    -2.31
    lós
    -2.25
    咝
    -2.20
     throng
    -2.17
    他会
    -2.16
    
    -2.14
    είου
    -2.13
    POSITIVE LOGITS
    .
    4.22
    ти
    3.16
    <
    2.73
     You
    2.53
     Then
    2.39
     Thus
    2.31
    ра
    2.30
            
    2.19
    tisgarh
    2.16
     ältere
    2.16
    Activations Density 0.001%

    No Known Activations