© 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. 117056
    Prev
    Next
    INDEX
    Explanations

    legal cases, foreign phrases, ethical situations, intense descriptors

    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
     Smith
    -0.06
    iope
    -0.06
     preparing
    -0.06
     Perfect
    -0.06
    atorul
    -0.05
    জিস্ট
    -0.05
    intersect
    -0.05
    perfect
    -0.05
    echo
    -0.05
    summer
    -0.05
    POSITIVE LOGITS
     exceedingly
    0.07
     amazingly
    0.07
     exceptionally
    0.06
     আপনার
    0.06
    不
    0.06
     spectacularly
    0.06
     unglaublich
    0.06
    ausible
    0.06
    शिंगटन
    0.06
     possibile
    0.06
    Activations Density 0.001%

    No Known Activations