© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69098
    Prev
    Next
    INDEX
    Explanations

    null, none, absence

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

    The neuron fires on code tokens that introduce actions—specifically on function‐call names and variable names on the left side of assignments.

    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
    vieja
    -0.91
    ñadir
    -0.88
    expliquer
    -0.85
     erhöhen
    -0.82
    alba
    -0.81
    ilight
    -0.79
     memasuki
    -0.79
    simple
    -0.79
     tradiciones
    -0.79
     Vordergrund
    -0.77
    POSITIVE LOGITS
     benign
    1.00
     positive
    0.91
    없
    0.90
     inexist
    0.87
     absence
    0.85
     none
    0.82
     industriel
    0.82
     هیچ
    0.81
    хва
    0.81
     null
    0.80
    Activations Density 0.005%

    No Known Activations