© 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. 22-GEMMASCOPE-RES-131K
    7. 53988
    Prev
    Next
    INDEX
    Explanations

    Yemen, The, Organization, Noise

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

    The neuron fires on promise‐rejection or exception‐throwing calls (e.g. Promise.reject/new TypeError).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.59
     its
    -1.52
     people
    -1.33
     first
    -1.27
     what
    -1.23
     everyone
    -1.23
     you
    -1.18
     have
    -1.17
     everybody
    -1.16
    價值
    -1.16
    POSITIVE LOGITS
    这些
    1.16
    łop
    1.10
    cles
    1.09
    在意
    1.09
     Эти
    1.09
     REALLY
    1.08
     Dinas
    1.08
    im
    1.07
    dding
    1.06
     essas
    1.05
    Activations Density 0.000%

    No Known Activations