© 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. 34869
    Prev
    Next
    INDEX
    Explanations

    loop initialization like `for (i = 0`

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

    The neuron fires on numeric literals in source code, especially the integer constants used in loop indices and array sizes.

    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
     exactly
    -1.04
    Manbalar
    -1.02
     observaciones
    -0.99
     MyApp
    -0.93
     capucha
    -0.93
    もう
    -0.92
     informazioni
    -0.91
     BufferedWriter
    -0.91
     AtomicInteger
    -0.89
     cardíaca
    -0.89
    POSITIVE LOGITS
     will
    1.00
     in
    0.96
     Affirm
    0.90
     piensan
    0.85
     équi
    0.84
    petite
    0.83
     wi
    0.83
    初步
    0.82
     Pre
    0.80
     thermique
    0.79
    Activations Density 0.004%

    No Known Activations