© 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
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1449
    Prev
    Next
    INDEX
    Explanations

    structure and composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
    Clone
    1.00
    کراچی
    0.96
    龟
    0.95
     rana
    0.91
    プール
    0.91
     Circus
    0.91
     transplantation
    0.89
    沙漠
    0.89
    infested
    0.88
    祭
    0.88
    POSITIVE LOGITS
     proteins
    1.83
     hormones
    1.80
     carbohydrates
    1.74
     vitamins
    1.73
     Vitamins
    1.70
     Proteins
    1.69
     acids
    1.67
     nutrients
    1.67
    proteins
    1.66
     lipids
    1.65
    Activations Density 0.596%

    No Known Activations