© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116077
    Prev
    Next
    INDEX
    Explanations

    like to be

    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
    Negative Logits
     digit
    -0.06
     বলিল
    -0.06
    Multicolored
    -0.06
     meteen
    -0.06
     zahval
    -0.06
     कितनी
    -0.06
    수는
    -0.06
     زیرا
    -0.06
     ক্ষমতাসীন
    -0.06
    无数
    -0.06
    POSITIVE LOGITS
    なし
    0.06
     appropriate
    0.06
    */
    0.06
     deixa
    0.06
     সমু
    0.06
    事先
    0.05
     डालकर
    0.05
     leave
    0.05
     trov
    0.05
     যথা
    0.05
    Activations Density 0.003%

    No Known Activations