© 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. 118913
    Prev
    Next
    INDEX
    Explanations

    code completion or specification

    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
     た
    -0.06
     miser
    -0.06
    iterate
    -0.06
     Do
    -0.06
    रक
    -0.06
     lin
    -0.06
    etermin
    -0.06
    <0xCA>
    -0.06
     कठिना
    -0.06
    ifferentiating
    -0.06
    POSITIVE LOGITS
     each
    0.06
     enforcement
    0.06
    ovac
    0.06
     каждую
    0.06
     diante
    0.06
     rented
    0.05
     হচ্ছে
    0.05
     oluyor
    0.05
     handsome
    0.05
    ্রমে
    0.05
    Activations Density 0.001%

    No Known Activations