© 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. 129278
    Prev
    Next
    INDEX
    Explanations

    house or home

    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
    ichtig
    -0.06
     così
    -0.06
     atm
    -0.06
     उपचुनाव
    -0.06
    aks
    -0.06
     કર્યા
    -0.06
     സാധാരണ
    -0.05
    cula
    -0.05
     returned
    -0.05
     assim
    -0.05
    POSITIVE LOGITS
    が含ま
    0.06
     केमिक
    0.06
     Maastricht
    0.06
     구현
    0.06
     bruised
    0.06
     வீடு
    0.06
     adunay
    0.06
    Согласно
    0.06
     согласно
    0.06
    明日
    0.06
    Activations Density 0.022%

    No Known Activations