© 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. 120849
    Prev
    Next
    INDEX
    Explanations

    invitation

    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
    افيه
    -0.06
     bakım
    -0.06
    随便
    -0.06
    넹
    -0.06
     davon
    -0.06
     morg
    -0.06
    basically
    -0.05
     Gino
    -0.05
    思い
    -0.05
     balcon
    -0.05
    POSITIVE LOGITS
     Invit
    0.06
     뿐
    0.06
    fordert
    0.06
    }_{\
    0.06
     the
    0.06
     invita
    0.06
     usuario
    0.06
    oyl
    0.06
     recombinant
    0.06
     identical
    0.05
    Activations Density 0.001%

    No Known Activations