© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21598
    Prev
    Next
    INDEX
    Explanations

    command-line usage instructions

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

    This neuron detects occurrences of the word “usage” (often as a heading) signaling usage instructions or examples.

    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
    邴
    -2.50
    鉏
    -2.48
    辚
    -2.47
    毟
    -2.38
    
    -2.30
    訁
    -2.30
    
    -2.27
    帏
    -2.27
    瘊
    -2.27
    傒
    -2.27
    POSITIVE LOGITS
    .
    2.72
    e
    2.72
     These
    2.61
     Before
    2.31
     Those
    2.19
     Although
    2.16
     Since
    2.11
    This
    2.09
    ,
    2.08
    You
    2.00
    Activations Density 0.003%

    No Known Activations