© 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. 27265
    Prev
    Next
    INDEX
    Explanations

    else block endings

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

    The neuron responds to statement terminators—especially semicolons—marking the ends of code statements.

    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
    -};
    -0.88
    SIGNAL
    -0.84
    проект
    -0.83
    NotNil
    -0.81
     lesión
    -0.78
    నే
    -0.74
    orteur
    -0.73
    REB
    -0.72
     Next
    -0.72
     Taking
    -0.71
    POSITIVE LOGITS
     otherwise
    1.01
     andet
    0.94
     însă
    0.88
    inda
    0.85
     nadru
    0.82
    élo
    0.81
     accus
    0.81
    issait
    0.80
    ække
    0.80
    菩萨
    0.78
    Activations Density 0.006%

    No Known Activations