© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    number or Nombre

    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
     chattel
    2.28
     IllegalArgument
    2.23
     Эти
    2.20
    ^{
    2.16
    topLeft
    2.04
     ^{
    2.04
     snapshots
    2.02
     fingert
    2.01
     среды
    2.01
    𝗮
    2.01
    POSITIVE LOGITS
    ட்சத்திர
    3.09
    م
    2.39
    subdir
    2.37
    buat
    2.36
    dür
    2.35
    მწიფ
    2.22
    chacha
    2.14
    cdf
    2.11
    ⣿
    2.10
    زد
    2.10
    Activations Density 0.550%

    No Known Activations