© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65686
    Prev
    Next
    INDEX
    Explanations

    function/method calls

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

    The neuron fires on code identifiers (variable or parameter names) in programming languages.

    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
     of
    -1.05
    SceneManagement
    -1.01
     from
    -0.95
    ційний
    -0.94
    迓
    -0.90
    듭
    -0.89
     jugend
    -0.89
     hien
    -0.88
    物は
    -0.88
     above
    -0.88
    POSITIVE LOGITS
    Unless
    0.90
    Consultar
    0.88
     Unless
    0.86
     erfordert
    0.84
    姫
    0.84
    ircut
    0.82
     Pilgrims
    0.82
     undangan
    0.81
     bescha
    0.80
     není
    0.79
    Activations Density 0.007%

    No Known Activations