© 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. 129077
    Prev
    Next
    INDEX
    Explanations

    professional unions

    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
     operador
    -0.06
     στό
    -0.06
     incent
    -0.06
     eccentric
    -0.06
    年纪
    -0.06
    ostrat
    -0.06
     renal
    -0.06
    叛
    -0.06
     aper
    -0.06
     Ammonia
    -0.06
    POSITIVE LOGITS
     respected
    0.07
     collectively
    0.07
     Collectively
    0.06
     protectors
    0.06
     collective
    0.06
     addressed
    0.06
     дальнейшем
    0.06
     collett
    0.06
     grievance
    0.06
     agreed
    0.06
    Activations Density 0.059%

    No Known Activations