© 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. 116863
    Prev
    Next
    INDEX
    Explanations

    lesion or percentage

    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
    Because
    -0.07
     dealing
    -0.06
    复杂
    -0.06
     Because
    -0.06
     вообще
    -0.06
    These
    -0.06
     অসম্ভব
    -0.06
     maintaining
    -0.06
     designing
    -0.05
     keeping
    -0.05
    POSITIVE LOGITS
    মুখে
    0.06
    rados
    0.06
     Perspekt
    0.06
     arit
    0.06
     aktuelle
    0.06
    torio
    0.06
     arke
    0.06
     psich
    0.06
     Vando
    0.06
     Quando
    0.06
    Activations Density 0.008%

    No Known Activations