© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    code function definitions

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

    The neuron spikes on the “<” and “>” tokens surrounding template or generic type parameters in code.

    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
     externally
    0.60
     estándar
    0.59
    трі
    0.58
     పరిశ
    0.56
     avanzados
    0.55
     slid
    0.55
     "@
    0.54
     sliding
    0.54
    欉
    0.54
     univers
    0.53
    POSITIVE LOGITS
    Arg
    0.67
    ALY
    0.58
    NTech
    0.58
     две
    0.58
    几个
    0.57
    な
    0.57
    OCH
    0.57
    兩個
    0.57
    引
    0.57
     अनेक
    0.57
    Activations Density 0.002%

    No Known Activations