© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8818
    Prev
    Next
    INDEX
    Explanations

    bulls are colorblind to red

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

    This neuron responds to numeric tokens—particularly decimal‐formatted measurements or citation counts.

    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
     Keywords
    0.79
    Keywords
    0.77
     Am
    0.73
     keywords
    0.70
     [<
    0.66
     小学
    0.66
     diarr
    0.63
     Keyword
    0.62
     应
    0.60
     Ис
    0.59
    POSITIVE LOGITS
    нес
    0.59
    اته
    0.54
    emaker
    0.52
    зывает
    0.52
    makes
    0.51
    носит
    0.51
     मानता
    0.51
    णार्‍या
    0.50
     exiled
    0.49
     affaire
    0.49
    Activations Density 0.010%

    No Known Activations