© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2193
    Prev
    Next
    INDEX
    Explanations

    dependency, cloud, recursion

    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_9_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
    ة
    4.26
    𝘨
    3.83
    𝐞
    3.69
    𝘦
    3.64
    𝐧
    3.59
    𝐄
    3.48
    𝘴
    3.37
    事情
    3.35
    𝐚
    3.35
    𝘳
    3.33
    POSITIVE LOGITS
    k
    3.86
    t
    3.53
    вання
    3.45
    יות
    3.39
    tive
    3.38
    si
    3.32
    ক
    3.31
    sel
    3.16
    𝗟
    3.13
    kval
    3.11
    Activations Density 0.653%

    No Known Activations