© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120838
    Prev
    Next
    INDEX
    Explanations

    Lists and percentages

    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
    Negative Logits
     more
    -0.08
     better
    -0.07
     bet
    -0.06
    する必要
    -0.06
     very
    -0.06
     اړ
    -0.06
     do
    -0.06
     entsprechend
    -0.06
     much
    -0.06
    www
    -0.06
    POSITIVE LOGITS
     connecting
    0.06
    </img>
    0.06
    Cuenta
    0.06
    عتها
    0.06
     goTo
    0.06
     formData
    0.06
    内置
    0.06
    덬
    0.06
     partager
    0.06
     saveData
    0.06
    Activations Density 0.004%

    No Known Activations