© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117862
    Prev
    Next
    INDEX
    Explanations

    numbers or preceding words

    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
     or
    -0.07
    真的
    -0.06
     >=
    -0.06
    那边
    -0.06
    正
    -0.05
     appreciable
    -0.05
     exhibited
    -0.05
    ADV
    -0.05
    ;')
    -0.05
    姊
    -0.05
    POSITIVE LOGITS
     verschiedenen
    0.07
    nicht
    0.06
     nicht
    0.06
     தவிர்க்க
    0.06
    Nicht
    0.06
     tergantung
    0.06
     있는
    0.06
     casos
    0.06
     通过
    0.06
     frei
    0.06
    Activations Density 0.041%

    No Known Activations