© 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. 34-GEMMASCOPE-RES-131K
    7. 84127
    Prev
    Next
    INDEX
    Explanations

    client pressures

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

    The neuron strongly activates on descriptive plot‐summary text (third‐person narrative describing what happens in the movie).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     souvent
    -1.43
     was
    -1.20
     parfois
    -1.16
    當時
    -1.16
    aroa
    -1.12
    歟
    -1.12
    bereiche
    -1.09
    跻
    -1.09
    vées
    -1.07
    often
    -1.05
    POSITIVE LOGITS
     queijo
    1.32
    klaus
    1.16
    珖
    1.14
    ılmıştır
    1.11
    各种
    1.11
     llamaba
    1.08
     potenci
    1.06
     secador
    1.06
    служба
    1.05
     lantaran
    1.05
    Activations Density 0.100%

    No Known Activations