© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    "on accuracy"

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

    The neuron is strongly activated by proper nouns and terms associated with musical artists, song titles, albums, and related entertainment context.

    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
    Susan
    0.71
     Susan
    0.64
    Wedgwood
    0.62
    桨
    0.61
    😃
    0.61
     symplectic
    0.60
     jaun
    0.59
     cheery
    0.58
    😀
    0.58
    🐞
    0.58
    POSITIVE LOGITS
     rappers
    1.85
     rapper
    1.74
     rapping
    1.55
     nigga
    1.45
     Eminem
    1.41
     rap
    1.35
     mixtape
    1.35
     Kanye
    1.32
     streetwear
    1.22
     Hip
    1.13
    Activations Density 0.446%

    No Known Activations