© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    created by

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

    The neuron detects “Created by…on” comment headers (i.e. the file‐creation metadata lines in code comments).

    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
     firſt
    -1.12
    魠
    -1.12
    ificantly
    -1.03
     partire
    -1.02
     visse
    -1.00
    ッセージ
    -0.98
    一点点
    -0.96
     ilha
    -0.96
    oeil
    -0.94
    forgotten
    -0.93
    POSITIVE LOGITS
     on
    1.93
     with
    1.81
     by
    1.68
     at
    1.16
     for
    0.98
    '
    0.97
    with
    0.93
    os
    0.88
    on
    0.88
    ar
    0.88
    Activations Density 0.005%

    No Known Activations