© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118737
    Prev
    Next
    INDEX
    Explanations

    just introducing explanations

    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
    でも
    -0.07
    How
    -0.06
    how
    -0.06
     how
    -0.06
     कशी
    -0.06
    Anyway
    -0.06
    ちゃんと
    -0.06
     reasonably
    -0.06
     anyway
    -0.06
    bag
    -0.05
    POSITIVE LOGITS
     decidió
    0.07
     CONTROL
    0.06
     dicho
    0.06
     아직
    0.06
     molti
    0.06
     দুই
    0.06
     hiện
    0.06
    👀
    0.06
    ितीय
    0.06
     selalu
    0.06
    Activations Density 0.010%

    No Known Activations