© 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. 129391
    Prev
    Next
    INDEX
    Explanations

    scale factors (2x, 3x)

    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
     ſ
    -0.06
     again
    -0.06
     त्याच
    -0.06
                          
    -0.06
     équ
    -0.06
    同时也
    -0.06
    亦
    -0.06
     giv
    -0.06
    不
    -0.06
     لدينا
    -0.05
    POSITIVE LOGITS
     Mc
    0.07
    avoz
    0.07
     from
    0.07
     while
    0.06
     Smith
    0.06
     системой
    0.06
     добавить
    0.06
     чином
    0.06
     прекра
    0.06
     a
    0.06
    Activations Density 0.003%

    No Known Activations