© 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. 103443
    Prev
    Next
    INDEX
    Explanations

    village in India

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

    The neuron responds in proportion to token length, i.e. it activates most strongly on longer 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
     бампер
    -1.09
     Filipino
    -1.08
     yacht
    -1.07
    logen
    -1.02
    vosti
    -1.02
     Mexican
    -0.99
     makam
    -0.99
     cruises
    -0.98
     valet
    -0.98
     Gauteng
    -0.98
    POSITIVE LOGITS
     village
    1.70
    Village
    1.65
     villagers
    1.59
    village
    1.48
     villager
    1.25
    VILL
    1.20
     villages
    1.14
     Village
    1.12
     VILLAGE
    1.05
     kerosene
    1.02
    Activations Density 0.046%

    No Known Activations