© 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. 128832
    Prev
    Next
    INDEX
    Explanations

    riverdale

    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
    とにかく
    -0.07
     three
    -0.07
     গৌর
    -0.06
     कैलकु
    -0.06
    ３
    -0.06
     மூன்று
    -0.06
     reken
    -0.06
     dilapidated
    -0.06
    வற்ற
    -0.06
    雖然
    -0.06
    POSITIVE LOGITS
     gibt
    0.06
     jef
    0.06
    ือง
    0.06
     бед
    0.06
    urent
    0.06
     Wm
    0.06
     из
    0.05
     PRE
    0.05
          
    0.05
     صورت
    0.05
    Activations Density 0.001%

    No Known Activations