© 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. 129013
    Prev
    Next
    INDEX
    Explanations

    numbers written out in various languages

    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
    好多
    -0.08
     MANY
    -0.06
     What
    -0.06
     Many
    -0.06
    What
    -0.06
     khẳng
    -0.06
     主
    -0.05
     분위
    -0.05
     viele
    -0.05
    いわ
    -0.05
    POSITIVE LOGITS
     three
    0.07
     four
    0.07
     четыре
    0.07
     három
    0.07
     Feld
    0.07
    ۳
    0.07
     trois
    0.06
     três
    0.06
     drei
    0.06
     nine
    0.06
    Activations Density 0.001%

    No Known Activations