© 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. 120558
    Prev
    Next
    INDEX
    Explanations

    section starters and questions

    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
    ldata
    -0.06
    values
    -0.06
     dovoljno
    -0.06
     belangrijke
    -0.06
    reciate
    -0.06
     অনুমান
    -0.06
    data
    -0.05
     sufficient
    -0.05
    説明
    -0.05
     graines
    -0.05
    POSITIVE LOGITS
     penguins
    0.06
     ottim
    0.06
     लोकार्पण
    0.06
     Voraussetzungen
    0.06
     créé
    0.06
     Legit
    0.06
    legt
    0.06
    各自
    0.06
     konkret
    0.06
     ожида
    0.06
    Activations Density 0.007%

    No Known Activations