© 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. 34-GEMMASCOPE-RES-131K
    4. 426
    Prev
    Next
    INDEX
    Explanations

    Closed Arrow

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

    This neuron responds to descriptive modifiers—particularly adjectives and adverbs that qualify or intensify content.

    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
    を
    -1.27
    など
    -1.18
    などを
    -1.04
    などの
    -1.02
    や
    -0.96
    atürk
    -0.94
    は
    -0.92
    <0xA3>
    -0.87
    good
    -0.84
    での
    -0.84
    POSITIVE LOGITS
     detriment
    0.98
    税込
    0.91
     daze
    0.90
    わけではない
    0.86
     accordance
    0.86
     atteindre
    0.85
     compréhension
    0.84
    ācijas
    0.83
    事です
    0.83
    ઘ
    0.83
    Activations Density 0.001%

    No Known Activations