© 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. 119481
    Prev
    Next
    INDEX
    Explanations

    giving orders or instructions

    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
     रखना
    -0.07
     предусмотре
    -0.07
     periodically
    -0.06
     debuted
    -0.06
     prüfen
    -0.06
    люби
    -0.06
     podkre
    -0.06
     प्रधाना
    -0.06
     pya
    -0.06
     оставить
    -0.06
    POSITIVE LOGITS
     низ
    0.06
     issu
    0.06
     instructions
    0.05
    バード
    0.05
    instructions
    0.05
     instructs
    0.05
     instructed
    0.05
    ্লাম
    0.05
     concerning
    0.05
    commands
    0.05
    Activations Density 0.019%

    No Known Activations