© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    Terraria

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

    The neuron fires on programming‐style identifiers and API/method call tokens (e.g. File.OpenText, StreamReader.Read, CosmosDB), marking code‐like technical terms.

    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
     dénom
    0.64
     ข้าง
    0.58
     IUnary
    0.57
    Most
    0.57
    ذك
    0.56
     녹
    0.55
    Uns
    0.55
     Most
    0.54
     ด้าน
    0.54
     Illustrations
    0.54
    POSITIVE LOGITS
     @
    0.76
    @"
    0.69
    (@"
    0.66
    @
    0.66
     (@
    0.64
    тение
    0.57
     trib
    0.57
    パンツ
    0.57
    ＠
    0.56
    (@
    0.56
    Activations Density 0.007%

    No Known Activations