© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1203
    Prev
    Next
    INDEX
    Explanations

    public static void

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

    The neuron fires on programming‐language keywords (e.g. static, const, function, private, def, let, public).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    A
    1.02
    V
    1.01
    Public
    0.99
    К
    0.98
    L
    0.98
    Am
    0.96
    F
    0.95
    H
    0.95
    Бе
    0.94
    B
    0.94
    POSITIVE LOGITS
     void
    1.28
     ActionResult
    1.09
     IEnumerable
    0.96
     gboolean
    0.91
     async
    0.91
     synchronized
    0.91
     ByteBuffer
    0.90
     IEnumerator
    0.88
     getNodeId
    0.88
     gameState
    0.87
    Activations Density 0.000%

    No Known Activations