© 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. 11648
    Prev
    Next
    INDEX
    Explanations

    github, microsoft, and programming libraries

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

    This neuron fires on dotted namespace or domain name fragments (e.g. package or URL components like “apache”, “org”, “maven”, “xml”, etc.).

    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
     優
    0.55
     Bulgar
    0.52
    }=(-
    0.52
     सम्पन्न
    0.50
    ……..
    0.50
     Literal
    0.49
     Finished
    0.49
    فانه
    0.48
     ……..
    0.48
    
    0.48
    POSITIVE LOGITS
    producto
    0.54
    posterous
    0.53
    喲
    0.53
     الخارجية
    0.52
     মুজিবর
    0.52
    groupId
    0.52
    addy
    0.52
     empire
    0.51
    impero
    0.51
     baryons
    0.50
    Activations Density 0.004%

    No Known Activations