© 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. 116860
    Prev
    Next
    INDEX
    Explanations

    eye parts, glasses, and facial features

    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
     aesthetics
    -0.06
     estética
    -0.06
     уже
    -0.06
     ಸ್ವಲ್ಪ
    -0.06
     by
    -0.06
     کچھ
    -0.06
     эсте
    -0.06
    已經
    -0.06
     espacial
    -0.06
     차량
    -0.06
    POSITIVE LOGITS
     консу
    0.06
    ressione
    0.06
     indications
    0.06
     véritable
    0.06
    oggles
    0.06
    危
    0.06
    赤
    0.06
    atians
    0.06
     Ganges
    0.06
    通常
    0.06
    Activations Density 0.003%

    No Known Activations