© 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. 84211
    Prev
    Next
    INDEX
    Explanations

    to attain / to accomplish / to welcome

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

    The neuron strongly responds to common short function words—especially prepositions like “by,” “to,” and “of.”

    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
    л
    -1.59
    на
    -1.52
    са
    -1.51
    не
    -1.45
    ри
    -1.44
    žena
    -1.38
    la
    -1.37
    你
    -1.34
    rophore
    -1.34
     would
    -1.33
    POSITIVE LOGITS
    私に
    1.53
    鉿
    1.51
    咙
    1.48
    喾
    1.45
    Gebruik
    1.43
     потребуется
    1.39
    就知道
    1.37
    ,\\
    1.37
    どうやって
    1.35
     susc
    1.34
    Activations Density 0.048%

    No Known Activations