© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35881
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming constructs

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

    This neuron detects leading indentation in code (runs of spaces or tabs at the start of lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Alternatively
    -0.78
    もない
    -0.77
     לצ
    -0.76
     variétés
    -0.75
     Exit
    -0.75
    łko
    -0.75
    ateľ
    -0.74
     autrement
    -0.74
     Aufenthalts
    -0.73
     begeistert
    -0.73
    POSITIVE LOGITS
     kamar
    0.85
     penulis
    0.83
     ocho
    0.82
     Chom
    0.82
     '',
    0.82
     trở
    0.82
     secolo
    0.82
    ḿ
    0.81
    porto
    0.79
    unjukan
    0.79
    Activations Density 0.008%

    No Known Activations