© 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. 89734
    Prev
    Next
    INDEX
    Explanations

    Ukraine, inflation, death tolls

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

    The neuron fires on section headings and titles (e.g. article headlines, subheadings, datelines, and other metadata lines).

    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
     http
    -0.90
    http
    -0.88
    ‪
    -0.84
    rester
    -0.84
    Trump
    -0.81
     kandungan
    -0.78
    ┐
    -0.76
    Obama
    -0.76
     Parke
    -0.76
    awesome
    -0.75
    POSITIVE LOGITS
     Ukraine
    3.05
     inflation
    2.56
     Inflation
    2.52
     Ukrainian
    2.41
    Inflation
    2.39
     Russia
    2.28
    Ukraine
    2.28
    inflation
    2.14
     Omicron
    2.03
     Ukrainians
    1.98
    Activations Density 0.036%

    No Known Activations