© 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. 119417
    Prev
    Next
    INDEX
    Explanations

    theme folder paths

    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
     تدخل
    -0.06
    矜
    -0.06
    bef
    -0.06
     keyed
    -0.06
     subsequent
    -0.06
     Subsequent
    -0.06
     ブルー
    -0.06
    °-
    -0.05
     verwenden
    -0.05
    burgh
    -0.05
    POSITIVE LOGITS
    你
    0.06
     διαφορε
    0.06
    위에
    0.06
    qtd
    0.06
    ision
    0.06
    "...
    0.06
    ydney
    0.06
     your
    0.06
    汽
    0.06
     jullie
    0.06
    Activations Density 0.007%

    No Known Activations