© 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. 128805
    Prev
    Next
    INDEX
    Explanations

    sender initials

    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
     అ
    -0.07
     because
    -0.06
    থায়
    -0.06
     ಅದರ
    -0.06
     making
    -0.06
    because
    -0.06
    अ
    -0.06
    lands
    -0.06
     প্রসঙ্গে
    -0.06
     எங்கள்
    -0.06
    POSITIVE LOGITS
     lenne
    0.07
     온라인
    0.06
     pourrait
    0.06
    administration
    0.06
    知県
    0.06
    exempt
    0.06
    รู
    0.06
     administration
    0.06
     rzeczyw
    0.06
    రావు
    0.06
    Activations Density 0.001%

    No Known Activations