© 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. 2255
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    .
    1.56
    你有
    1.40
     ench
    1.39
     dwelt
    1.39
    ОО
    1.38
    ou
    1.37
    ü
    1.35
    .”
    1.34
    んばんは
    1.34
     wiem
    1.33
    POSITIVE LOGITS
    ங்கிணை
    1.64
    is
    1.57
     compless
    1.53
    ిన
    1.49
    젝트
    1.44
     стали
    1.43
     relativi
    1.42
    лед
    1.39
    ும்போது
    1.38
    ฀
    1.37
    Activations Density 0.022%

    No Known Activations