© 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. 119433
    Prev
    Next
    INDEX
    Explanations

    television series and shows

    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
     tanta
    -0.06
     something
    -0.06
     ihren
    -0.06
     eines
    -0.06
     caballero
    -0.06
     jednego
    -0.06
     would
    -0.06
    something
    -0.06
     salah
    -0.06
    多样
    -0.06
    POSITIVE LOGITS
    νοντας
    0.06
     unprocessed
    0.06
     가까
    0.06
     particles
    0.06
     input
    0.06
     اسٹ
    0.06
     particle
    0.06
     частиц
    0.06
     ವಿಶ
    0.06
    接近
    0.06
    Activations Density 0.010%

    No Known Activations