© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111315
    Prev
    Next
    INDEX
    Explanations

    Quasar Sample or Vue

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

    words related to quasars and astronomical objects in scientific text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting specialized astrophysics terminology, especially references to quasars, active galactic nuclei, and related extragalactic phenomena.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    笆
    -1.49
     других
    -1.48
     Your
    -1.47
     you
    -1.43
     "",
    -1.42
     Vielzahl
    -1.41
    ామ
    -1.39
     мы
    -1.39
     hebdomada
    -1.39
    -"
    -1.38
    POSITIVE LOGITS
     out
    1.30
    Constantes
    1.22
    Thumbs
    1.22
     dará
    1.20
     to
    1.19
    julio
    1.16
     with
    1.13
    틴
    1.13
     such
    1.11
    marty
    1.11
    Activations Density 0.038%

    No Known Activations