© 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. 128648
    Prev
    Next
    INDEX
    Explanations

    Hail holy queen, My Darling Soul, twinkle little

    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
    บาง
    -0.06
     uptake
    -0.05
     finden
    -0.05
    നിന്ന്
    -0.05
     antennes
    -0.05
     «
    -0.05
     стать
    -0.05
     underdog
    -0.05
     diventare
    -0.05
     algún
    -0.05
    POSITIVE LOGITS
    视觉
    0.08
     yaklaşık
    0.07
    視覺
    0.07
     gibi
    0.07
     이제
    0.07
     such
    0.07
     గురించి
    0.06
     is
    0.06
     typically
    0.06
     çok
    0.06
    Activations Density 0.005%

    No Known Activations