© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 720
    Prev
    Next
    INDEX
    Explanations

    Guerras, Raft

    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
    ्स
    4.68
    น้อง
    4.48
    d
    4.38
    y
    4.30
    t
    4.29
    m
    4.28
    க்
    4.19
    ことができる
    4.12
    م
    4.12
    اً
    4.11
    POSITIVE LOGITS
    ş
    3.24
    pping
    2.98
    х
    2.72
    ри
    2.70
    pped
    2.67
    que
    2.54
    ԁ
    2.44
    ⅾ
    2.37
    ɗ
    2.34
    ht
    2.34
    Activations Density 1.043%

    No Known Activations