© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120144
    Prev
    Next
    INDEX
    Explanations

    existing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Continuing
    -0.06
     ഉദ്
    -0.06
     continuing
    -0.06
     Sama
    -0.06
     Ma
    -0.06
     पहिल्या
    -0.06
    Continuing
    -0.06
    continue
    -0.06
     القاعد
    -0.06
     milestone
    -0.05
    POSITIVE LOGITS
     existing
    0.08
    existing
    0.08
     Existing
    0.08
     EXISTING
    0.07
    既存
    0.07
    原本
    0.07
    Existing
    0.07
    が増
    0.07
     existentes
    0.07
     increased
    0.07
    Activations Density 0.099%

    No Known Activations