© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7684
    Prev
    Next
    INDEX
    Explanations

    explore alternative options

    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
    𝐭
    2.82
    𝐟
    2.68
    껏
    2.61
    𝐠
    2.57
    可以将
    2.51
    𝐩
    2.44
    𝐤
    2.43
     backbone
    2.38
    𝐨
    2.35
    𝐥
    2.34
    POSITIVE LOGITS
    на
    3.11
    i
    2.58
    ла
    2.42
    يئة
    2.36
    ي
    2.34
    zione
    2.32
    тие
    2.24
    ја
    2.24
    те
    2.20
    дна
    2.15
    Activations Density 0.234%

    No Known Activations