© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    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
    rews
    1.38
    tion
    1.28
    ﻚ
    1.28
     fikk
    1.26
    ဉ်
    1.25
     další
    1.22
    keley
    1.21
    焼
    1.20
    fica
    1.19
    tim
    1.19
    POSITIVE LOGITS
    Д
    1.13
    DOS
    1.12
    ха
    1.10
    На
    1.09
    ма
    1.08
    ชน์
    1.06
    नरी
    1.04
    ند
    1.04
    То
    1.01
    Ти
    1.01
    Activations Density 0.000%

    No Known Activations