© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    quantifying small amounts

    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
    eau
    2.57
    𝐬
    2.45
    𝐭
    2.30
    𝐡
    2.28
    𝐧
    2.26
    یز
    2.25
    াদের
    2.21
    oz
    2.21
    𝐮
    2.20
    𝐝
    2.17
    POSITIVE LOGITS
     dozen
    4.22
    dozen
    3.37
     hundred
    3.35
     thousand
    3.14
    ture
    2.68
    thousand
    2.64
    ি
    2.56
    Hundred
    2.51
    te
    2.48
    몇
    2.47
    Activations Density 0.065%

    No Known Activations