© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13126
    Prev
    Next
    INDEX
    Explanations

    based on the rest of us

    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_17_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
    uš
    1.06
    ся
    1.05
    ما
    1.00
    с
    0.98
    voll
    0.97
    ijiet
    0.96
    다른
    0.94
    stedt
    0.94
    rends
    0.93
    𝘀
    0.93
    POSITIVE LOGITS
     计算
    1.32
     লক্ষণ
    1.29
    ের
    1.29
    いる
    1.26
    িয়ে
    1.26
    計算
    1.24
    ্নি
    1.24
     hired
    1.22
     corpora
    1.21
     fadeIn
    1.21
    Activations Density 0.002%

    No Known Activations