© 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. 119198
    Prev
    Next
    INDEX
    Explanations

    of the"}, linked, requires

    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
     ເ
    -0.06
     their
    -0.06
     free
    -0.06
    Ι
    -0.06
     worldwide
    -0.05
     moderately
    -0.05
     आमच्या
    -0.05
     ล
    -0.05
    ড়াই
    -0.05
    worldwide
    -0.05
    POSITIVE LOGITS
    igned
    0.07
     begann
    0.07
    屹
    0.06
     pixels
    0.06
     yaşanan
    0.06
    amethasone
    0.06
    都需要
    0.06
     требуют
    0.06
     ricerca
    0.06
     meadows
    0.06
    Activations Density 0.002%

    No Known Activations