© 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. 38096
    Prev
    Next
    INDEX
    Explanations

    baby boomers age", dequeue reusable cell

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

    The neuron is tuned to pick up legal/boilerplate terms (e.g. ©, “Copyright,” “permission,” “copy,” “redistribute,” “modify,” etc.) commonly found in software‐license and copyright headers.

    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
    ELER
    -0.77
    𝐋
    -0.76
    Payment
    -0.73
    𝐂
    -0.70
     reformer
    -0.69
    eler
    -0.68
    CDU
    -0.67
     Reformation
    -0.67
    Luca
    -0.66
     Valuation
    -0.66
    POSITIVE LOGITS
     Keine
    0.69
    hasia
    0.68
    akana
    0.65
    phe
    0.63
    pha
    0.62
     cse
    0.62
    яд
    0.61
    andler
    0.60
     ffs
    0.60
    wiring
    0.60
    Activations Density 0.062%

    No Known Activations