© 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. 119074
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and variables

    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
     a
    -0.07
     के
    -0.07
     एक
    -0.07
     peuvent
    -0.06
     একটি
    -0.06
     في
    -0.06
    空間
    -0.06
     wcześniej
    -0.06
     on
    -0.06
     feminine
    -0.06
    POSITIVE LOGITS
    工作人员
    0.06
    =======
    0.06
    こういう
    0.06
     cosidd
    0.06
     EXACT
    0.06
     ഇത്തരം
    0.06
     quatre
    0.06
     ACTUAL
    0.06
     এরকম
    0.05
     fulfills
    0.05
    Activations Density 0.003%

    No Known Activations