© 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. 129959
    Prev
    Next
    INDEX
    Explanations

    endorsed, was, attached, Rhein, Cold

    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
     sambil
    -0.08
    하면서
    -0.07
     Charging
    -0.07
     third
    -0.07
     year
    -0.07
     Carefully
    -0.06
    第三
    -0.06
    지막
    -0.06
     година
    -0.06
    关联
    -0.06
    POSITIVE LOGITS
    ON
    0.06
    OM
    0.06
    Ej
    0.06
    OD
    0.06
    нутри
    0.06
    OT
    0.06
    早
    0.06
     планы
    0.05
    คิด
    0.05
    OC
    0.05
    Activations Density 0.001%

    No Known Activations