© 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. 128774
    Prev
    Next
    INDEX
    Explanations

    definitions, suffixes with 'iatric', country codes

    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
     marshall
    -0.06
     vai
    -0.06
     extinguish
    -0.06
     ತಯಾರ
    -0.06
     career
    -0.05
     culmin
    -0.05
    ńst
    -0.05
     garnered
    -0.05
     quantifiable
    -0.05
     basic
    -0.05
    POSITIVE LOGITS
     oba
    0.07
     pessoas
    0.07
     тот
    0.06
     Função
    0.06
    seriously
    0.06
     giddy
    0.06
     klient
    0.06
                             
    0.06
    autorité
    0.06
    pea
    0.06
    Activations Density 0.001%

    No Known Activations