© 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. 129669
    Prev
    Next
    INDEX
    Explanations

    scientific journals and methods

    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
    ಂದು
    -0.07
     niemals
    -0.07
    xRt
    -0.06
     нашим
    -0.06
    లను
    -0.06
     ?)
    -0.06
    rival
    -0.06
     আমাদের
    -0.06
     ক্ল
    -0.06
     tutkim
    -0.05
    POSITIVE LOGITS
     under
    0.06
    在该
    0.06
     Demp
    0.06
    体重
    0.06
     eder
    0.06
     আসল
    0.06
     ander
    0.06
    つもり
    0.05
     LSD
    0.05
     perturbations
    0.05
    Activations Density 0.001%

    No Known Activations