© 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. 120510
    Prev
    Next
    INDEX
    Explanations

    override keywords

    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
     including
    -0.08
    including
    -0.07
     achieve
    -0.07
     এবং
    -0.07
     kullan
    -0.06
     fys
    -0.06
     뜻
    -0.06
     মেট্র
    -0.06
     استفاده
    -0.06
     maintains
    -0.06
    POSITIVE LOGITS
     possibilities
    0.07
     ezzel
    0.06
    的可能性
    0.06
     perhaps
    0.06
    可能性
    0.06
     conceivable
    0.06
    がある
    0.06
    Ｕ
    0.06
    有
    0.06
    者
    0.06
    Activations Density 0.001%

    No Known Activations