© 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. 120243
    Prev
    Next
    INDEX
    Explanations

    dates and meetings

    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
    request
    -0.06
     semblable
    -0.06
     sent
    -0.06
     എത്ര
    -0.06
    That
    -0.06
     आढळ
    -0.06
     transmettre
    -0.06
    La
    -0.05
     confirmed
    -0.05
    For
    -0.05
    POSITIVE LOGITS
     the
    0.08
     interpretation
    0.07
     لیکن
    0.07
    কিন্তু
    0.06
    🤣
    0.06
     우리가
    0.06
    interpretation
    0.06
    混乱
    0.06
     involves
    0.06
     해석
    0.06
    Activations Density 0.006%

    No Known Activations