© 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. 34214
    Prev
    Next
    INDEX
    Explanations

    code structures and assignments

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

    The neuron fires on numeric literals (numbers) in the code.

    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
     budgeted
    -1.00
    íncia
    -0.87
    Ment
    -0.84
    Arbit
    -0.83
    Herzlich
    -0.83
     begren
    -0.81
    KID
    -0.81
    MAM
    -0.78
    Chats
    -0.78
     warmen
    -0.78
    POSITIVE LOGITS
    lioz
    0.90
     Most
    0.83
    Most
    0.81
     Default
    0.79
     domy
    0.78
    Default
    0.77
     Não
    0.73
     Measures
    0.73
     Tesla
    0.73
     Hull
    0.72
    Activations Density 0.060%

    No Known Activations