© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2267
    Prev
    Next
    INDEX
    Explanations

    financial reports and section markers

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

    The neuron fires on the standard corporate‐disclosure boilerplate phrases—especially “forward-looking statements in these remarks” and “risk factors” sections.

    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
     yerine
    -0.81
    eiras
    -0.79
     zodat
    -0.77
    一场
    -0.77
    ôr
    -0.77
     đón
    -0.75
    unanje
    -0.74
    删
    -0.73
    Axiom
    -0.73
    ртка
    -0.72
    POSITIVE LOGITS
    Report
    0.95
    Annual
    0.95
     Quarterly
    0.93
     Report
    0.90
     our
    0.89
     периоди
    0.87
     diskusi
    0.85
     Annual
    0.85
     quarterly
    0.84
     and
    0.83
    Activations Density 0.013%

    No Known Activations