© 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. 6407
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    ύτε
    2.28
    ४
    2.28
    ی
    2.24
    اً
    2.22
    ➖➖
    2.12
    Ни
    2.11
    Cuánt
    2.10
     druk
    2.09
    \,
    2.05
    于是
    2.01
    POSITIVE LOGITS
    ه
    4.43
    quela
    3.45
    ী
    3.40
    o
    3.36
    er
    3.36
    دخل
    3.11
    →</
    3.07
    هي
    3.05
    ו
    2.91
    ა
    2.90
    Activations Density 0.584%

    No Known Activations