© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10500
    Prev
    Next
    INDEX
    Explanations

    emitted from

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

    The neuron fires on the “Author” metadata label (i.e. whenever the document lists “Author:” before a name).

    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
     нього
    0.66
    녀
    0.66
     dotato
    0.66
     afficher
    0.64
    随着
    0.63
     SLASH
    0.63
     وتق
    0.63
     diversité
    0.63
    ╾
    0.63
     него
    0.62
    POSITIVE LOGITS
    мит
    0.67
     Reve
    0.66
     Milne
    0.66
    ál
    0.65
     Coron
    0.64
     Davies
    0.64
    ewell
    0.64
    ij
    0.63
    haus
    0.62
     دفتر
    0.62
    Activations Density 0.000%

    No Known Activations