© 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. 118751
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and citations

    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
    현재
    -0.07
     сега
    -0.07
     বর্তমানে
    -0.07
     to
    -0.06
    বর্তমানে
    -0.06
     сейчас
    -0.06
     Şu
    -0.06
     onların
    -0.06
     onları
    -0.06
     тях
    -0.06
    POSITIVE LOGITS
     interd
    0.06
     unsuspecting
    0.06
     wybr
    0.05
    )
    0.05
    ARE
    0.05
     Interim
    0.05
     a
    0.05
     Inter
    0.05
    স্থ
    0.05
    aried
    0.05
    Activations Density 0.001%

    No Known Activations