© 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. 119551
    Prev
    Next
    INDEX
    Explanations

    ends with suffix

    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
     വിൽപ്പന
    -0.06
    存在する
    -0.06
     को
    -0.06
    த்தினை
    -0.06
     गिनती
    -0.06
     born
    -0.06
     Cal
    -0.06
     bı
    -0.06
     З
    -0.06
    始め
    -0.06
    POSITIVE LOGITS
     sends
    0.08
    harmed
    0.06
     harmed
    0.06
    妥
    0.06
     send
    0.06
     sending
    0.06
     makes
    0.06
     recent
    0.06
     respective
    0.06
     yada
    0.06
    Activations Density 0.003%

    No Known Activations