© 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. 118148
    Prev
    Next
    INDEX
    Explanations

    role and responsibilities

    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
     because
    -0.07
    !!
    -0.07
     simple
    -0.06
    Family
    -0.06
    !!!
    -0.06
    A
    -0.06
    Because
    -0.06
     avec
    -0.06
     with
    -0.05
     karena
    -0.05
    POSITIVE LOGITS
     ਆਪਣੇ
    0.08
     своего
    0.08
     establishes
    0.07
    自分が
    0.07
     establish
    0.07
    其它
    0.07
     determines
    0.07
     integrates
    0.07
     swojego
    0.07
    自己在
    0.06
    Activations Density 0.015%

    No Known Activations