© 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. 24-GEMMASCOPE-2-RES-16K
    7. 16166
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

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

    The neuron detects wire‐service datelines or syndication headers (e.g. “GLOBE NEWSWIRE,” Marketwired, 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_24_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
     Üniversitesi
    0.29
     Ji
    0.28
    meyer
    0.28
    Ji
    0.28
    ।
    0.27
    ة
    0.27
     Baru
    0.27
    ﺔ
    0.26
     Oyun
    0.26
     gồm
    0.26
    POSITIVE LOGITS
     hexagons
    0.36
     untapped
    0.34
    ногда
    0.34
     polygons
    0.32
     isomorphisms
    0.32
     lobes
    0.31
     maniera
    0.30
     extremities
    0.30
     coarser
    0.30
     functors
    0.30
    Activations Density 0.001%

    No Known Activations