© 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. 129515
    Prev
    Next
    INDEX
    Explanations

    mechanisms of action

    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
     ਅਤੇ
    -0.09
     మరియు
    -0.07
     आणि
    -0.07
     ಮತ್ತು
    -0.07
    Atl
    -0.07
     और
    -0.07
     diseñado
    -0.06
     আৰু
    -0.06
     восста
    -0.06
    rowski
    -0.06
    POSITIVE LOGITS
     All
    0.07
    㘿
    0.07
     refuge
    0.06
     the
    0.06
     these
    0.06
    这些人
    0.06
     The
    0.06
     AU
    0.05
    All
    0.05
     Com
    0.05
    Activations Density 0.018%

    No Known Activations