© 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. 93859
    Prev
    Next
    INDEX
    Explanations

    table references

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

    The neuron fires on numbered references to tables or figures (e.g. “Table 1,” “Table 3,” “Scheme 1,” etc.).

    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
    如图
    -1.08
    bilde
    -0.92
    klub
    -0.91
    waarden
    -0.85
    ImageLoader
    -0.84
    tellungs
    -0.82
    här
    -0.81
    ياس
    -0.81
    bedien
    -0.81
    EventLoop
    -0.80
    POSITIVE LOGITS
     table
    2.33
    Table
    1.91
     Table
    1.74
     tables
    1.73
    table
    1.51
    TABLE
    1.48
     Tables
    1.41
    Tables
    1.39
     TABLE
    1.23
    ctable
    1.14
    Activations Density 0.003%

    No Known Activations