© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 863
    Prev
    Next
    INDEX
    Explanations

    section titles or table headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comment
    0.73
     چنین
    0.69
     kann
    0.68
     takich
    0.68
    或許
    0.66
    也許
    0.66
    할
    0.66
     ولا
    0.65
    Suppose
    0.65
     هذه
    0.65
    POSITIVE LOGITS
     vibrancy
    0.70
    profissional
    0.68
    issantes
    0.68
    ूरती
    0.63
    virt
    0.58
    isiert
    0.58
    size
    0.58
    ampil
    0.57
    
    0.57
    ுடைய
    0.57
    Activations Density 0.207%

    No Known Activations