© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100669
    Prev
    Next
    INDEX
    Explanations

    thereof

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

    The neuron strongly activates on the formal technical/legal linking term “thereof” (and its equivalents like Portuguese “dela”), i.e. pronominal “of it/them” constructions.

    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
    𖥦
    -1.94
    鴣
    -1.87
    Hanya
    -1.83
    欵
    -1.79
    куртка
    -1.74
    Hermoso
    -1.74
    ஂ
    -1.73
    Geograf
    -1.71
    Kondisi
    -1.70
    ureusement
    -1.68
    POSITIVE LOGITS
     to
    1.86
    :
    1.76
    The
    1.70
    ра
    1.55
     {
    1.53
        
    1.52
     –
    1.50
    <h3>
    1.49
                
    1.46
    <h6>
    1.46
    Activations Density 0.005%

    No Known Activations