© 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. 116649
    Prev
    Next
    INDEX
    Explanations

    following 'Understanding' a specific condition

    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
    なぜ
    -0.06
    чит
    -0.06
    чает
    -0.06
    け
    -0.06
    zont
    -0.06
     বেরিয়ে
    -0.05
     भले
    -0.05
     watering
    -0.05
    ิติ
    -0.05
     absence
    -0.05
    POSITIVE LOGITS
     соответствующих
    0.08
     these
    0.08
    कायदा
    0.07
     соответству
    0.07
     entsprechenden
    0.07
     obey
    0.07
     unsuspecting
    0.07
    相应
    0.07
     específicas
    0.07
     this
    0.07
    Activations Density 0.001%

    No Known Activations