© 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. 128489
    Prev
    Next
    INDEX
    Explanations

    exchange factor

    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
     raggiunto
    -0.06
     सीमा
    -0.06
    极限
    -0.06
     limite
    -0.06
    Limits
    -0.06
     ambitious
    -0.06
    然後
    -0.06
     మొక్క
    -0.05
     serupa
    -0.05
     लिमिट
    -0.05
    POSITIVE LOGITS
    可以直接
    0.06
    Explicit
    0.06
     konfl
    0.06
    茣
    0.06
    สำหรับ
    0.06
    )=>
    0.06
     카
    0.06
    Hosted
    0.06
     relief
    0.06
    insert
    0.06
    Activations Density 0.002%

    No Known Activations