© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2577
    Prev
    Next
    INDEX
    Explanations

    bracket enclosed lists

    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
    К
    3.44
    в
    3.38
    가
    2.99
    一来
    2.96
     heed
    2.90
     sino
    2.90
     dàng
    2.86
    𝐵
    2.86
     jeste
    2.83
    𝑅
    2.81
    POSITIVE LOGITS
    tion
    4.11
     lineColorSpace
    3.75
    tor
    3.42
    t
    3.40
    اً
    3.39
    tio
    3.29
    
    3.16
    ted
    3.13
    tad
    3.07
    tır
    3.07
    Activations Density 0.228%

    No Known Activations