© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    cmake and ninja build tools

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

    The neuron fires on proper names and named entities (e.g., person names, character names, organizations, or product titles).

    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
     stra
    0.62
     strap
    0.58
     lactose
    0.58
     straps
    0.55
     megal
    0.52
    神戸
    0.52
     Asturias
    0.51
    🚠
    0.51
     boarding
    0.51
     buckle
    0.50
    POSITIVE LOGITS
     ninja
    1.25
    Ninja
    1.24
     Ninja
    1.22
     Naruto
    1.14
    ninja
    1.10
     shinobi
    1.02
    忍者
    0.88
    Kon
    0.84
     Sasuke
    0.84
     chakra
    0.82
    Activations Density 0.070%

    No Known Activations