© 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. 463
    Prev
    Next
    INDEX
    Explanations

    Prince Princess Masako Prudentópolis

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

    This neuron responds to capitalized name tokens, i.e. parts of people’s proper 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
    s
    0.32
     Hogwarts
    0.27
     b
    0.27
     high
    0.27
     l
    0.26
     s
    0.26
     g
    0.26
    ’
    0.26
     “
    0.26
     HVAC
    0.26
    POSITIVE LOGITS
    ار
    0.25
    ิน
    0.25
    angleOf
    0.23
    unkte
    0.23
    aterina
    0.23
    𝒚
    0.23
     Ли
    0.23
    iscilla
    0.22
    ettamente
    0.22
    وش
    0.22
    Activations Density 0.555%

    No Known Activations