© 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. 4765
    Prev
    Next
    INDEX
    Explanations

    The Trevor Project

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

    The neuron fires strongly on isolated named‐entity tokens—proper names, acronyms, or software/tool names.

    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
     januar
    0.57
    '],
    0.55
     ');
    0.55
     Addison
    0.55
     amelyet
    0.55
    ']
    0.54
     februar
    0.54
     ");
    0.54
    ")]
    0.54
     <-
    0.54
    POSITIVE LOGITS
    oglycos
    0.63
     отверсти
    0.61
     грун
    0.56
    ruptcy
    0.56
    μμα
    0.55
     மற்றும்
    0.54
    avement
    0.54
    ampuan
    0.53
    ority
    0.52
    般的
    0.52
    Activations Density 0.013%

    No Known Activations