© 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. 24-GEMMASCOPE-2-RES-16K
    4. 14252
    Prev
    Next
    INDEX
    Explanations

    javascript variable declarations

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

    The neuron flags proper nouns and other named‐entity terms, like personal names, team names, and distinctive titles.

    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
    Ш
    1.02
    il
    0.79
    ри
    0.77
    Polynomial
    0.76
    评估
    0.75
    ை
    0.75
    ం
    0.74
    Би
    0.74
    П
    0.74
    И
    0.74
    POSITIVE LOGITS
     sellest
    0.91
     pierwsze
    0.87
     exacerb
    0.85
     suitors
    0.85
     vassals
    0.84
     strangers
    0.84
     suaves
    0.83
     hospice
    0.83
     effluents
    0.83
     pitiful
    0.82
    Activations Density 4.655%

    No Known Activations