© 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. 14643
    Prev
    Next
    INDEX
    Explanations

    scrub or scour

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

    The neuron activates whenever it sees the root “scrub” (in any form such as scrub, scrubbing, scrubbers, scrubland, etc.).

    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
    ⟣
    -2.70
    甃
    -2.61
    gesterone
    -2.39
     избежать
    -2.38
    葯
    -2.34
    
    -2.31
    
    -2.27
     다른
    -2.23
     anderen
    -2.22
    鮰
    -2.22
    POSITIVE LOGITS
    ;
    2.59
     главным
    2.48
     gefeiert
    2.25
    寕
    2.16
    dersfield
    2.05
     dirigida
    2.02
     impressive
    1.98
     gruppo
    1.98
     aims
    1.95
     verfolgt
    1.95
    Activations Density 0.002%

    No Known Activations