© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    Baltic states and languages

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

    The neuron strongly responds to the use of the typographic apostrophe—i.e. tokens containing curly quotes in contractions (like you’re, it’s, won’t).

    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
    México
    0.82
    Cantidad
    0.74
    contenedor
    0.73
    ógrafo
    0.72
     méxico
    0.72
    🌵
    0.69
    thiop
    0.68
     TRANSPORTURI
    0.68
     venezolano
    0.68
    
    0.66
    POSITIVE LOGITS
     Latvian
    2.11
     Latvia
    1.98
     Estonian
    1.92
     Lithuanian
    1.86
     Eesti
    1.80
     Estonia
    1.79
     Latvij
    1.75
     Baltic
    1.74
     Riga
    1.71
     Vilnius
    1.70
    Activations Density 0.068%

    No Known Activations