© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3747
    Prev
    Next
    INDEX
    Explanations

    This neuron detects scientific (Latin‐style) names and taxonomy terms, especially genus–species and other biological classification labels.

    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
     reconsideration
    1.09
     учетом
    0.95
     thoughtfulness
    0.93
     acquies
    0.88
     परिवर्तन
    0.88
     स्थगित
    0.87
    時間を
    0.86
    躊
    0.86
     નિર્ણય
    0.85
    タイミング
    0.85
    POSITIVE LOGITS
     nowadays
    1.18
     esistono
    1.10
     finns
    1.09
     mostly
    1.05
     chiefly
    1.04
     cultivars
    1.03
     mainly
    1.02
     existem
    1.01
     kebanyakan
    1.00
     usually
    0.98
    Activations Density 0.279%

    No Known Activations