© 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. 116527
    Prev
    Next
    INDEX
    Explanations

    legal cases beginning with "This"

    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
     incluindo
    -0.07
     kvalitet
    -0.07
     powerfully
    -0.07
     gebruik
    -0.06
     dalla
    -0.06
     reflects
    -0.06
     після
    -0.06
     prodigious
    -0.06
     magnifique
    -0.06
     Até
    -0.06
    POSITIVE LOGITS
     примерно
    0.06
    .
    0.06
    How
    0.06
    ii
    0.06
    oun
    0.06
     സംഘ
    0.06
    Why
    0.06
    7
    0.06
     இவற்ற
    0.05
     engagements
    0.05
    Activations Density 0.001%

    No Known Activations