© 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. 117477
    Prev
    Next
    INDEX
    Explanations

    how it relates to

    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
     PLoS
    -0.07
     different
    -0.06
     dependiendo
    -0.06
     ಉತ್ತಮ
    -0.06
     sambil
    -0.06
     Different
    -0.06
     വ്യത്യസ്ത
    -0.06
     استخدم
    -0.06
     poté
    -0.06
     unterschied
    -0.05
    POSITIVE LOGITS
     where
    0.08
     четыре
    0.06
    她在
    0.06
     যেখানে
    0.06
     केश
    0.06
     நான்கு
    0.06
     όπου
    0.06
    cially
    0.06
     donde
    0.05
     як
    0.05
    Activations Density 0.094%

    No Known Activations