© 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. 103037
    Prev
    Next
    INDEX
    Explanations

    legal and administrative identifiers

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

    The neuron is triggered by alphanumeric reference codes (e.g. docket numbers, filing IDs, or other document identifiers).

    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
    História
    -1.40
    Often
    -1.38
     outras
    -1.36
     し
    -1.35
    Typically
    -1.30
    érien
    -1.30
    瑧
    -1.26
    نسي
    -1.23
    tanleria
    -1.19
    Probl
    -1.19
    POSITIVE LOGITS
     about
    1.73
     then
    1.72
     --
    1.58
     –
    1.48
     —
    1.34
     Then
    1.31
     a
    1.30
    -
    1.30
     asiática
    1.25
    BOTH
    1.24
    Activations Density 0.058%

    No Known Activations