© 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. 106655
    Prev
    Next
    INDEX
    Explanations

    source context files and origins

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

    The neuron fires on occurrences of the word “source” (in either capitalization), marking any “source” or “Source” token.

    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
    美女
    -0.80
    enak
    -0.79
     elev
    -0.76
     hacker
    -0.75
    ाहरण
    -0.72
    ammlung
    -0.72
     Cinderella
    -0.71
    藉
    -0.71
     legitim
    -0.71
    懂
    -0.71
    POSITIVE LOGITS
     jsi
    0.89
     deaktiviert
    0.88
     getSource
    0.79
    વે
    0.75
    Ár
    0.75
    っぴ
    0.75
     anunciar
    0.74
     GAO
    0.73
     coinvol
    0.73
     portata
    0.73
    Activations Density 0.029%

    No Known Activations