© 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. 104386
    Prev
    Next
    INDEX
    Explanations

    intuition and internal senses

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

    The neuron activates on words that express personal intuition or internal mental states (e.g. feeling, hunch, doubt, foreboding, inkling).

    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
              
    -1.51
     to
    -1.50
    guigu
    -1.49
     ancianos
    -1.48
                        
    -1.35
                                  
    -1.34
    完成了
    -1.34
                      
    -1.34
     pensamiento
    -1.30
                           
    -1.28
    POSITIVE LOGITS
     that
    1.76
    żenie
    1.61
    tabria
    1.57
     Hinblick
    1.55
    outWeight
    1.47
    鸸
    1.42
    tigte
    1.41
     другие
    1.41
    ுகள்
    1.40
    idends
    1.39
    Activations Density 0.011%

    No Known Activations