© 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. 13569
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    The neuron strongly responds to long sequences of digits in ISBN‐style bibliographic identifiers.

    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
     HAS
    0.68
    你有
    0.64
     KNOW
    0.63
    刎
    0.63
    ে
    0.63
    Polynomial
    0.62
     。
    0.61
    ।
    0.61
     Knows
    0.61
    丿
    0.60
    POSITIVE LOGITS
     kitabı
    0.70
     philanth
    0.64
     seura
    0.64
     saints
    0.63
     shrines
    0.63
    uyoruz
    0.63
     villains
    0.62
     horns
    0.61
     pebbles
    0.61
     sages
    0.61
    Activations Density 0.066%

    No Known Activations