© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    a lot of

    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
    هِ
    2.23
    𝓁
    2.23
    ٽ
    2.21
     evidenced
    2.16
     dibuat
    2.15
    ﻼ
    2.10
    istence
    2.10
    ٕ
    2.10
     disusun
    2.09
    यानक
    2.09
    POSITIVE LOGITS
    teries
    3.24
    i
    3.21
    en
    2.75
    ल
    2.70
    ので
    2.64
    क
    2.62
    el
    2.57
    ten
    2.54
    te
    2.42
    י
    2.41
    Activations Density 0.206%

    No Known Activations