© 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. 116592
    Prev
    Next
    INDEX
    Explanations

    antibodies or immunoblotting

    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
     Exempl
    -0.06
     ভোক্তার
    -0.06
    :":
    -0.05
    FeO
    -0.05
    ,.
    -0.05
     необходимо
    -0.05
    너
    -0.05
    <0x9C>
    -0.05
     क्षेत्रीय
    -0.05
     राजस्थान
    -0.05
    POSITIVE LOGITS
    淩
    0.07
    私人
    0.07
    ntilde
    0.06
    〞
    0.06
    плуа
    0.06
    靳
    0.06
    Kong
    0.06
     KOM
    0.06
     حاول
    0.06
     Saif
    0.06
    Activations Density 0.041%

    No Known Activations