© 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. 16002
    Prev
    Next
    INDEX
    Explanations

    optional and null values

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

    The neuron flags tokens that denote optional or nullable type annotations (e.g. “null,” “bool,” “?,” “Optional”).

    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
    妧
    -1.31
     rompi
    -1.26
     boîtes
    -1.16
    绉
    -1.15
     boucles
    -1.09
    えっ
    -1.07
     Nr
    -1.06
     geladeira
    -1.05
    他还
    -1.05
    somewhere
    -1.05
    POSITIVE LOGITS
     if
    1.35
     can
    1.08
     depending
    1.04
     to
    1.04
     that
    1.01
    tainable
    0.98
     lainnya
    0.98
    новременно
    0.96
    Xiaomi
    0.92
     aler
    0.91
    Activations Density 0.003%

    No Known Activations