© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14550
    Prev
    Next
    INDEX
    Explanations

    black onyx, Division, trumpet, matrices

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

    The main thing this neuron does is spot proper names and formal entities (e.g. organization names, titles, places).

    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
    Tottenham
    1.00
    mainan
    0.93
    beding
    0.90
    Throwable
    0.89
     або
    0.89
     phép
    0.89
    mpl
    0.86
    몫
    0.85
     ขาย
    0.84
    ij
    0.84
    POSITIVE LOGITS
     Boo
    1.03
    なのですが
    1.00
     Bits
    0.96
     Basics
    0.93
    리로
    0.91
     וב
    0.91
     stanza
    0.90
     paragraphs
    0.89
     Beware
    0.88
    输入
    0.88
    Activations Density 5.173%

    No Known Activations