© 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. 116699
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time periods

    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
    謁
    -0.08
     giurid
    -0.07
     to
    -0.07
    𝐽
    -0.07
    合計
    -0.07
     indelible
    -0.07
    少なくとも
    -0.07
     achievable
    -0.07
     수를
    -0.07
     bijective
    -0.07
    POSITIVE LOGITS
     помогает
    0.06
     helps
    0.06
     Erick
    0.05
     سه
    0.05
     उनके
    0.05
     speaks
    0.05
    বহ
    0.05
    ère
    0.05
     three
    0.05
     사람
    0.05
    Activations Density 0.035%

    No Known Activations