© 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. 84428
    Prev
    Next
    INDEX
    Explanations

    hunting and harvesting

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

    The neuron selectively fires on words naming human activities—especially gerund action nouns (e.g. “poisoning,” “hunting,” “harvesting,” “pursuing”) and other verbs referring to managed or regulated actions.

    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
     ASD
    -0.81
    ficador
    -0.79
    ジャパン
    -0.79
    Invit
    -0.78
    めない
    -0.77
     Dios
    -0.75
    ěji
    -0.75
    ASD
    -0.74
     ought
    -0.74
     proporción
    -0.74
    POSITIVE LOGITS
    possession
    1.29
     possession
    1.27
     harvest
    1.20
     Possession
    1.09
    harvest
    1.05
     killing
    0.95
     Harvest
    0.94
    Harvest
    0.90
     seasons
    0.86
    killing
    0.86
    Activations Density 0.012%

    No Known Activations