© 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. 22-GEMMASCOPE-RES-131K
    7. 26875
    Prev
    Next
    INDEX
    Explanations

    form validation and post

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

    The neuron fires on “@” instance‐variable markers in code.

    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
    chtenstein
    -1.03
    uerung
    -0.96
     общий
    -0.93
     связь
    -0.92
     noirs
    -0.90
     различных
    -0.90
     различные
    -0.89
     olika
    -0.88
    SCRIPT
    -0.87
    ENDIAN
    -0.87
    POSITIVE LOGITS
    muñeca
    0.84
     your
    0.81
     you
    0.79
     teapot
    0.79
     allow
    0.78
     पनि
    0.77
     hört
    0.77
     kerjasama
    0.77
     gefährlich
    0.76
     Öffnungszeiten
    0.76
    Activations Density 0.001%

    No Known Activations