© 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. 119825
    Prev
    Next
    INDEX
    Explanations

    new cases diagnosed

    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
     مثل
    -0.07
     cuja
    -0.06
     seperti
    -0.06
     such
    -0.06
     like
    -0.06
    اته
    -0.06
    FACTORY
    -0.06
     स्टैट
    -0.06
     низкой
    -0.06
     وقد
    -0.06
    POSITIVE LOGITS
    最後まで
    0.06
     abandon
    0.06
     subsurface
    0.05
     তৎ
    0.05
     lasciare
    0.05
    dekat
    0.05
     обоих
    0.05
     তুম
    0.05
     يصير
    0.05
     herm
    0.05
    Activations Density 0.007%

    No Known Activations