© 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. 118563
    Prev
    Next
    INDEX
    Explanations

    JUDGE

    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
     robust
    -0.07
     міжнарод
    -0.06
     rozwoju
    -0.06
     التكامل
    -0.06
     strong
    -0.06
     partnering
    -0.06
     robustness
    -0.06
     spin
    -0.05
     Wies
    -0.05
     difficult
    -0.05
    POSITIVE LOGITS
    總統
    0.07
    式の
    0.07
     저장
    0.06
     determinato
    0.06
    像是
    0.06
     denoting
    0.06
    ственности
    0.06
    ственными
    0.06
     대통령
    0.06
     setiap
    0.06
    Activations Density 0.009%

    No Known Activations