© 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. 117514
    Prev
    Next
    INDEX
    Explanations

    without

    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
     wiederum
    -0.06
     megfelelő
    -0.06
     แก
    -0.06
     आएगा
    -0.06
    以后
    -0.06
    自分の
    -0.06
    用来
    -0.05
     PAST
    -0.05
    另一
    -0.05
     Past
    -0.05
    POSITIVE LOGITS
     without
    0.07
     including
    0.07
     contro
    0.06
     senza
    0.06
     без
    0.06
     Cleveland
    0.06
     площади
    0.06
     highway
    0.06
     instante
    0.06
     precursor
    0.06
    Activations Density 0.004%

    No Known Activations