© 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. 118516
    Prev
    Next
    INDEX
    Explanations

    :(

    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
     very
    -0.09
     screaming
    -0.06
    very
    -0.06
     research
    -0.06
    equivalent
    -0.06
     tremendous
    -0.06
     بسیار
    -0.06
     quite
    -0.06
     remarkably
    -0.06
     vrlo
    -0.06
    POSITIVE LOGITS
     பின்பற்ற
    0.06
    私が
    0.06
    我已经
    0.06
     distancia
    0.06
    已
    0.06
    ों
    0.06
    Israel
    0.06
     మరియు
    0.06
    其它
    0.06
     და
    0.06
    Activations Density 0.002%

    No Known Activations