© 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. 34-GEMMASCOPE-RES-131K
    7. 80669
    Prev
    Next
    INDEX
    Explanations

    source code file

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

    The neuron detects boilerplate license‐and‐copyright header language in code comments and metadata.

    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
     COMING
    -0.78
    ﻃ
    -0.75
     Clive
    -0.71
    dwarf
    -0.71
     Cliffs
    -0.71
    Taw
    -0.68
     FORECAST
    -0.67
    maksi
    -0.67
    mbad
    -0.66
     Livro
    -0.65
    POSITIVE LOGITS
     proceedings
    0.69
    gand
    0.67
     Gang
    0.67
    ></
    0.65
    वन
    0.65
    SizeF
    0.64
    為何
    0.64
     priori
    0.64
     judicial
    0.63
     Banking
    0.63
    Activations Density 0.086%

    No Known Activations