© 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. 117596
    Prev
    Next
    INDEX
    Explanations

    company policies and guidelines

    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
     সবচেয়ে
    -0.07
     of
    -0.06
     to
    -0.06
     darkening
    -0.06
     comparisons
    -0.06
     mengucapkan
    -0.06
     বন্দুক
    -0.06
     clarification
    -0.06
     অবা
    -0.06
     pondering
    -0.06
    POSITIVE LOGITS
     rules
    0.10
     правила
    0.09
     guidelines
    0.09
     laws
    0.09
     policies
    0.09
    ポリシー
    0.08
     protocol
    0.08
     قوانین
    0.08
     Guidelines
    0.08
     Rules
    0.08
    Activations Density 0.016%

    No Known Activations