© 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. 14900
    Prev
    Next
    INDEX
    Explanations

    Category markers and code execution

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

    The neuron responds to rare or distinctive tokens—especially unusual proper names and uncommon code identifiers.

    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
    Rozmiar
    -1.12
     forskellige
    -0.94
     dirigeants
    -0.93
    Dá
    -0.93
     estufa
    -0.92
     teclas
    -0.91
     keyCode
    -0.91
    genuine
    -0.91
     Enquanto
    -0.90
    lový
    -0.90
    POSITIVE LOGITS
     donald
    1.00
    if
    0.97
    věr
    0.93
     Tenden
    0.92
    e
    0.91
    else
    0.91
    тися
    0.91
    RE
    0.90
    set
    0.90
    the
    0.87
    Activations Density 0.035%

    No Known Activations