© 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. 130165
    Prev
    Next
    INDEX
    Explanations

    names of companies/organizations/groups

    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
     according
    -0.06
     for
    -0.06
    they
    -0.06
                          
    -0.06
     bych
    -0.06
    fromDate
    -0.06
     начали
    -0.06
    সাব
    -0.06
     annat
    -0.06
     باوجود
    -0.06
    POSITIVE LOGITS
     también
    0.07
     hundreds
    0.07
     également
    0.07
     možda
    0.06
     also
    0.06
     कई
    0.06
     several
    0.06
     hordes
    0.06
     Hundreds
    0.06
     sürec
    0.06
    Activations Density 0.001%

    No Known Activations