© 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. 109192
    Prev
    Next
    INDEX
    Explanations

    causes something to be

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

    The neuron lights up on content‐dense, multi­syllable technical and scientific terms (i.e. formal jargon and domain-specific nouns).

    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
    volves
    -1.01
    volve
    -0.88
     فاض
    -0.87
     خواهد
    -0.85
    ๘
    -0.85
    chieben
    -0.84
     nuoc
    -0.83
    ါ
    -0.81
    视着
    -0.81
    idences
    -0.80
    POSITIVE LOGITS
     makes
    2.11
     helps
    1.74
     allows
    1.71
    ทำให้
    1.59
     ensures
    1.59
     means
    1.59
     khiến
    1.59
     باعث
    1.57
     allow
    1.47
     ensure
    1.47
    Activations Density 0.113%

    No Known Activations