© 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. 116519
    Prev
    Next
    INDEX
    Explanations

    personal digital assistants

    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
     Gaming
    -0.07
     любом
    -0.06
    Gaming
    -0.06
     Amplifier
    -0.06
     เด็ก
    -0.06
    ত্যাগ
    -0.06
     amplifying
    -0.06
    enfants
    -0.06
     어린
    -0.06
    damn
    -0.06
    POSITIVE LOGITS
     business
    0.08
     timeless
    0.06
     бизнес
    0.06
     CPD
    0.06
    business
    0.06
    Business
    0.06
     APIs
    0.06
     бизне
    0.06
     BUSINESS
    0.06
     ऐसा
    0.06
    Activations Density 0.011%

    No Known Activations