© 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. 129296
    Prev
    Next
    INDEX
    Explanations

    talking, let, actually, turn, why, innovative

    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
     memper
    -0.06
     resembles
    -0.06
     inclui
    -0.06
     এছাড়া
    -0.06
     primavera
    -0.06
    /**/*.
    -0.06
    county
    -0.06
     Istituto
    -0.06
    unless
    -0.06
    的味道
    -0.06
    POSITIVE LOGITS
    !!!!!!
    0.06
    „
    0.06
    !!!!!!!
    0.06
    この
    0.06
    !!!!!!!!
    0.06
     নামাজের
    0.06
    你就
    0.06
    مد
    0.06
     (=
    0.06
     ต่อ
    0.06
    Activations Density 0.089%

    No Known Activations