© 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. 10-GEMMASCOPE-RES-131K
    7. 61211
    Prev
    Next
    INDEX
    Explanations

    farm and farmville

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

    The neuron detects occurrences of the word “farm” (in any context or casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    缡
    -2.89
    ឵
    -2.89
    𓆸
    -2.81
    骓
    -2.73
    
    -2.72
    罍
    -2.72
     parachoque
    -2.64
    狨
    -2.63
    猹
    -2.63
    UGHS
    -2.63
    POSITIVE LOGITS
    ↵↵
    3.66
    -
    3.41
    )
    3.16
    (
    3.16
     If
    3.16
    ve
    3.06
    b
    2.88
    ?
    2.78
    o
    2.67
    m
    2.64
    Activations Density 0.009%

    No Known Activations