© 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. 129228
    Prev
    Next
    INDEX
    Explanations

    html structure elements

    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
     Its
    -0.08
     its
    -0.06
     దాని
    -0.06
     മുഴുവ
    -0.06
     إلا
    -0.06
    करना
    -0.06
     infusion
    -0.06
    瓒
    -0.06
     certain
    -0.06
     اكثر
    -0.06
    POSITIVE LOGITS
     also
    0.07
    同样
    0.07
     також
    0.07
    同樣
    0.06
     सहित
    0.06
     также
    0.06
    同
    0.06
     along
    0.06
     fifth
    0.06
    第五
    0.06
    Activations Density 0.011%

    No Known Activations