© 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. 92331
    Prev
    Next
    INDEX
    Explanations

    land redistribution

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

    The neuron lights up on substantial “content” words—nouns, verbs, adjectives, adverbs, and other informative tokens—especially in formal or legal-style text, rather than on purely grammatical or filler words.

    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
    Стро
    -0.86
     暖
    -0.79
    onMouse
    -0.78
     Switching
    -0.77
    Requires
    -0.76
    ⊄
    -0.75
    Disable
    -0.74
    busch
    -0.73
    Row
    -0.71
    ="#
    -0.70
    POSITIVE LOGITS
     land
    2.02
     redistribution
    1.55
     redistribute
    1.44
     Land
    1.34
     Redist
    1.29
     distribution
    1.22
    Land
    1.19
     LAND
    1.13
    LAND
    1.09
     Distribution
    1.05
    Activations Density 0.011%

    No Known Activations