© 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. 128309
    Prev
    Next
    INDEX
    Explanations

    evidence for future research

    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
     coś
    -0.06
    rahm
    -0.06
    हून
    -0.06
    phosphorylation
    -0.06
     最近
    -0.06
     সংক্রান্ত
    -0.06
     промышленности
    -0.06
     armament
    -0.05
     তড়
    -0.05
     하나의
    -0.05
    POSITIVE LOGITS
     বেশী
    0.06
     Reduced
    0.06
    high
    0.06
     high
    0.06
     alot
    0.06
    ствует
    0.06
    HIGH
    0.06
     there
    0.06
     réduction
    0.06
    anced
    0.06
    Activations Density 0.034%

    No Known Activations