© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90339
    Prev
    Next
    INDEX
    Explanations

    starvation and hunger

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

    references to famine, starvation, and food shortages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on numeric tokens—especially digits and multi‐digit sequences such as years and quantities.

    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
     আপ
    -0.87
     FORMAT
    -0.85
    FORMAT
    -0.84
    aday
    -0.77
    Frag
    -0.75
    format
    -0.75
    矣
    -0.75
     ব্য
    -0.74
    frag
    -0.73
     FRAG
    -0.73
    POSITIVE LOGITS
     famine
    3.95
     starvation
    3.08
     hunger
    2.86
     fam
    2.53
     starving
    2.44
    hunger
    2.38
     starve
    2.38
     Hunger
    2.25
     голо
    2.20
    Hunger
    2.20
    Activations Density 0.034%

    No Known Activations