© 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. 59813
    Prev
    Next
    INDEX
    Explanations

    allegedly engaging in misconduct

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

    The neuron lights up on business‐news contexts—especially company and executive names alongside monetary amounts or finance/legal action terms.

    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
     other
    -1.16
     any
    -1.15
     all
    -1.11
     usually
    -1.04
     only
    -1.01
     noticeably
    -1.00
     considerably
    -0.97
     new
    -0.93
     interestingly
    -0.92
     what
    -0.91
    POSITIVE LOGITS
     its
    1.27
     протяжении
    1.10
     certaines
    1.09
     LEAGUE
    1.06
    nearly
    1.05
    hundreds
    1.05
    thousands
    1.05
    millions
    1.01
     misschien
    1.01
     improper
    1.01
    Activations Density 0.070%

    No Known Activations