© 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. 109203
    Prev
    Next
    INDEX
    Explanations

    paroxetine treatment label

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

    code related to byte manipulation or processing in programming languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on programming‐style tokens—especially license header phrases (e.g. “All rights reserved,” “BSD-style license”) and code/import keywords and identifiers.

    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
     control
    -0.74
     DRE
    -0.68
    atest
    -0.68
     Stuhl
    -0.68
    APPENDICES
    -0.67
    撑
    -0.66
     Control
    -0.65
     znan
    -0.64
     progress
    -0.63
    warf
    -0.62
    POSITIVE LOGITS
     dolphins
    0.76
    newcommand
    0.75
     dancing
    0.74
     szó
    0.73
    Export
    0.73
    ージェ
    0.71
    Altitude
    0.71
    uanya
    0.70
     exporting
    0.69
    lably
    0.69
    Activations Density 0.098%

    No Known Activations