© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8794
    Prev
    Next
    INDEX
    Explanations

    AIart, Healthcare, Laravel, Aristocracy, Conflict

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

    The neuron detects proper names (named entities) such as institutions, locations, brands, and people.

    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
     pertama
    0.51
     for
    0.49
     meds
    0.49
     The
    0.48
     info
    0.48
     first
    0.48
     (*)
    0.48
     के
    0.47
     only
    0.47
     से
    0.46
    POSITIVE LOGITS
    orada
    0.44
    uldades
    0.41
    oslav
    0.40
    iefer
    0.40
    spacerItem
    0.39
     cosidd
    0.38
    府中
    0.38
    zeniem
    0.37
    aito
    0.36
    bardziej
    0.36
    Activations Density 1.596%

    No Known Activations