© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9871
    Prev
    Next
    INDEX
    Explanations

    JSON

    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_22_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
     inclusion
    1.02
     সম্পন্ন
    0.91
    tsConfig
    0.85
     trattamento
    0.84
     स्वागत
    0.83
     going
    0.83
     bringing
    0.83
    +(
    0.82
    ρίζ
    0.81
     zi
    0.81
    POSITIVE LOGITS
     कार्
    0.92
    university
    0.91
    大學
    0.91
     Staff
    0.90
    Staff
    0.90
    大学
    0.86
    운
    0.86
    מונה
    0.86
    staff
    0.85
    apture
    0.85
    Activations Density 0.033%

    No Known Activations