© 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. 119988
    Prev
    Next
    INDEX
    Explanations

    friend or foe

    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
     wenn
    -0.08
     from
    -0.07
     adorn
    -0.06
     রঙ
    -0.06
    Toilet
    -0.06
     seit
    -0.06
    🎩
    -0.06
     desde
    -0.06
     roof
    -0.06
     topped
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    など
    0.08
    などに
    0.07
     போன்றவற்ற
    0.07
    等
    0.07
     ইত্যাদি
    0.07
     berkaitan
    0.06
     etcétera
    0.06
    等方面
    0.06
     ইত্যা
    0.06
    Activations Density 0.002%

    No Known Activations