© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 428
    Prev
    Next
    INDEX
    Explanations

    and then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
     zwar
    1.12
    romeda
    1.01
    ક
    0.94
    rogens
    0.90
    щите
    0.85
    uin
    0.85
    ри
    0.84
    р
    0.83
    ோ
    0.83
    蜍
    0.82
    POSITIVE LOGITS
    一个
    0.87
     ακόμα
    0.86
     eivät
    0.80
     ακόμη
    0.80
    vem
    0.77
     hardly
    0.77
    _,
    0.77
    また
    0.75
    其
    0.72
     etiam
    0.69
    Activations Density 0.381%

    No Known Activations