© 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. 119506
    Prev
    Next
    INDEX
    Explanations

    singer-songwriter / his own / his first

    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
    第二
    -0.06
     первая
    -0.06
     second
    -0.06
     второй
    -0.06
     fourth
    -0.06
     Ă
    -0.06
     tweede
    -0.05
    correctAns
    -0.05
    ,...
    -0.05
     auf
    -0.05
    POSITIVE LOGITS
    单独
    0.08
     leftover
    0.07
     باقي
    0.07
     शेष
    0.06
     заду
    0.06
     asignar
    0.06
    льній
    0.06
     자유
    0.06
     separado
    0.06
    пів
    0.06
    Activations Density 0.007%

    No Known Activations