© 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. 116891
    Prev
    Next
    INDEX
    Explanations

    EV-DO, SUMO, DENSE, MOUSE, FAVVA, INTAROS, MEFV

    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
     చిత్ర
    -0.06
     aforesaid
    -0.06
    Then
    -0.06
     قب
    -0.06
     Independent
    -0.06
    prising
    -0.06
     then
    -0.06
    kh
    -0.06
    sound
    -0.06
     Popular
    -0.06
    POSITIVE LOGITS
     также
    0.07
    తాయి
    0.06
     perturbations
    0.06
    endereco
    0.06
     نیز
    0.06
     também
    0.06
     થયા
    0.06
     doivent
    0.06
     donnent
    0.06
     viennent
    0.06
    Activations Density 0.005%

    No Known Activations