© 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. 117013
    Prev
    Next
    INDEX
    Explanations

    special offers, partners, or support

    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
     यांची
    -0.07
     kelahiran
    -0.06
     seven
    -0.06
     again
    -0.06
    ্রের
    -0.06
     الثانية
    -0.06
     eradication
    -0.06
     four
    -0.06
     erneut
    -0.06
     toll
    -0.06
    POSITIVE LOGITS
    指向
    0.06
    (=
    0.06
     reference
    0.05
    想要
    0.05
     budu
    0.05
    ajara
    0.05
    鏘
    0.05
    special
    0.05
     encuentro
    0.05
    刚才
    0.05
    Activations Density 0.005%

    No Known Activations