© 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. 116450
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     różne
    -0.08
     если
    -0.07
     अगर
    -0.07
     こんな
    -0.07
     이런
    -0.07
     diferentes
    -0.07
     দুটো
    -0.07
     nếu
    -0.07
     다른
    -0.07
     olika
    -0.07
    POSITIVE LOGITS
    Wr
    0.06
    чатку
    0.06
     যেটি
    0.06
    !,
    0.06
    ‼
    0.05
    之後
    0.05
     (;
    0.05
     követ
    0.05
    τία
    0.05
     கிமு
    0.05
    Activations Density 0.001%

    No Known Activations