© 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. 117609
    Prev
    Next
    INDEX
    Explanations

    those seeds

    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
     valuing
    -0.05
     percib
    -0.05
    rama
    -0.05
     대통령
    -0.05
    不论
    -0.05
     enige
    -0.05
    bfc
    -0.05
     який
    -0.05
    सामान्य
    -0.05
    uc
    -0.05
    POSITIVE LOGITS
     those
    0.09
    those
    0.09
     Those
    0.08
    Those
    0.08
     aqueles
    0.08
     celles
    0.07
     outras
    0.07
     aquelas
    0.07
     ferramentas
    0.07
     OTHER
    0.07
    Activations Density 0.001%

    No Known Activations