© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118463
    Prev
    Next
    INDEX
    Explanations

    aggregate, shift, RUN, large, Books, Rejection, Electric

    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
     will
    -0.08
     dismissing
    -0.07
     goes
    -0.07
    蟒
    -0.07
     are
    -0.07
     strives
    -0.07
     another
    -0.07
     became
    -0.06
     also
    -0.06
     no
    -0.06
    POSITIVE LOGITS
     這個
    0.05
     Этот
    0.05
    ه
    0.05
     Inj
    0.05
    Oh
    0.05
    ท
    0.05
    ////
    0.05
     zweimal
    0.05
     제일
    0.05
    人的
    0.05
    Activations Density 0.001%

    No Known Activations