© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 111039
    Prev
    Next
    INDEX
    Explanations

    thorough cleaning actions

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

    This neuron detects action words for cleaning, washing, scrubbing, soaking, or otherwise removing dirt or debris.

    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
     çalışan
    -0.92
    Based
    -0.90
     templado
    -0.89
     namelijk
    -0.88
     känna
    -0.88
     based
    -0.88
     on
    -0.85
    ácií
    -0.84
    essentiel
    -0.84
     obtained
    -0.82
    POSITIVE LOGITS
     thoroughly
    1.52
    twice
    1.28
     Thorough
    1.20
     thorough
    1.16
     twice
    1.09
     gründ
    1.06
     THOR
    1.05
     metic
    1.03
     جيد
    1.03
     obses
    1.02
    Activations Density 0.027%

    No Known Activations