© 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. 22293
    Prev
    Next
    INDEX
    Explanations

    regular or frequent

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

    The neuron detects occurrences of the word “regular.”

    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
    ntk
    -1.60
     یکی
    -1.59
     bolsillos
    -1.59
    -1.54
    ANIEL
    -1.51
     sportifs
    -1.49
    щата
    -1.48
    Slf
    -1.48
     sellado
    -1.46
    
    -1.45
    POSITIVE LOGITS
     in
    2.52
    d
    1.86
     on
    1.72
    na
    1.64
     at
    1.60
    B
    1.53
    呜呜
    1.51
     çünkü
    1.50
    ent
    1.48
     out
    1.48
    Activations Density 0.011%
    No Known Activations