© 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. 20503
    Prev
    Next
    INDEX
    Explanations

    renewed hope and status

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

    The neuron primarily detects occurrences of “renew” (especially “renewed”) and its close morphological variants.

    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
        
    -1.59
     لیتر
    -1.53
     ไม่มี
    -1.52
    比较
    -1.43
     construire
    -1.42
     cómod
    -1.42
     adored
    -1.41
     icône
    -1.41
     dichos
    -1.41
     resalt
    -1.41
    POSITIVE LOGITS
    ’
    1.73
    ktionen
    1.31
    他们
    1.29
     should
    1.28
     снова
    1.27
     płasz
    1.27
     they
    1.26
    ?」
    1.23
    anın
    1.23
     anew
    1.23
    Activations Density 0.020%

    No Known Activations