© 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. 69152
    Prev
    Next
    INDEX
    Explanations

    side of things

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

    This neuron fires on the generic filler noun “things,” especially in phrases like “of things” or “side of things.”

    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
     verschillen
    -1.86
    皤
    -1.83
     清新
    -1.68
     volledige
    -1.65
     ongeveer
    -1.60
     algemene
    -1.60
     eenvou
    -1.58
     oorspron
    -1.55
     uitgebre
    -1.55
     Diciembre
    -1.52
    POSITIVE LOGITS
    )
    2.64
    </h3>
    1.85
    1
    1.74
    u
    1.71
    ca
    1.70
    j
    1.65
    ad
    1.63
    v
    1.61
     Ее
    1.59
    s
    1.58
    Activations Density 0.014%

    No Known Activations