© 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. 117645
    Prev
    Next
    INDEX
    Explanations

    weight stigmatization

    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
     Multimedia
    -0.06
    📍
    -0.06
     the
    -0.06
     Logical
    -0.06
     Av
    -0.06
     companies
    -0.05
     Matemat
    -0.05
    Multimedia
    -0.05
    ara
    -0.05
     British
    -0.05
    POSITIVE LOGITS
     सप
    0.07
     we
    0.07
     scanning
    0.06
     తిరిగి
    0.06
     উভয়
    0.06
    事實
    0.06
     slashed
    0.06
     losers
    0.06
     stumpage
    0.06
     ثلاثه
    0.06
    Activations Density 0.003%

    No Known Activations