© 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. 80735
    Prev
    Next
    INDEX
    Explanations

    code cache settings

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

    The neuron fires on terms related to caching or stored session/cache settings.

    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
     Funktionalität
    -1.82
     that
    -1.66
     Aktivität
    -1.58
     Behaup
    -1.52
     he
    -1.50
     Begleitung
    -1.48
     einzigartige
    -1.48
     Hinsicht
    -1.45
     Verbesserung
    -1.43
     관련
    -1.43
    POSITIVE LOGITS
    。
    1.54
     να
    1.44
    r
    1.43
    点此
    1.38
    无论
    1.38
    请输入
    1.37
    Väl
    1.36
    的
    1.34
    h
    1.34
     Она
    1.34
    Activations Density 0.028%

    No Known Activations