© 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. 34-GEMMASCOPE-RES-131K
    7. 76821
    Prev
    Next
    INDEX
    Explanations

    window hints

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

    This neuron responds to all-caps code identifiers (especially OpenGL/GLFW constants and macros with underscores).

    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
    kontroll
    -0.88
     Nếu
    -0.85
    Vol
    -0.85
     Bedi
    -0.85
    Wrap
    -0.84
     baden
    -0.82
     runde
    -0.82
    NSUserDefaults
    -0.82
     Elsevier
    -0.81
     wrap
    -0.81
    POSITIVE LOGITS
     Профиль
    0.77
     Forderungen
    0.73
    Elin
    0.71
     Henne
    0.71
    Torn
    0.71
    Buongiorno
    0.69
    下单
    0.69
    פיה
    0.69
     HIR
    0.68
     double
    0.68
    Activations Density 0.026%

    No Known Activations