© 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. 34-GEMMASCOPE-RES-131K
    7. 81696
    Prev
    Next
    INDEX
    Explanations

    code blocks

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

    The neuron activates on identifiers that are being introduced in code (i.e. variable names at their declaration sites).

    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
     then
    -0.92
     perché
    -0.88
     अन्य
    -0.78
    身为
    -0.77
     máquina
    -0.77
     затем
    -0.77
    jutant
    -0.75
    zumaki
    -0.75
    깨
    -0.74
    DeleteBehavior
    -0.74
    POSITIVE LOGITS
    ighed
    0.86
    strijden
    0.85
     提示
    0.84
    țe
    0.84
    Rojo
    0.83
    //=
    0.82
     ancora
    0.82
    ggiato
    0.81
    stim
    0.80
     croy
    0.80
    Activations Density 0.024%

    No Known Activations