© 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. 117613
    Prev
    Next
    INDEX
    Explanations

    future trends or possibilities

    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
    切实
    -0.06
    没想到
    -0.06
    もっと
    -0.06
     ควร
    -0.06
     gostaria
    -0.06
    ですが
    -0.05
     bienvenidos
    -0.05
     gehabt
    -0.05
    无论是
    -0.05
     exact
    -0.05
    POSITIVE LOGITS
    可能會
    0.07
     may
    0.07
     może
    0.07
    可能会
    0.07
     might
    0.07
     перемен
    0.07
     potrà
    0.06
     amea
    0.06
     poderá
    0.06
     Trend
    0.06
    Activations Density 0.053%

    No Known Activations