© 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. 117712
    Prev
    Next
    INDEX
    Explanations

    GNU GPL license

    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
     meanwhile
    -0.06
     rather
    -0.06
     fascinated
    -0.06
     captivated
    -0.06
    igraph
    -0.06
     Eliminate
    -0.05
     accurately
    -0.05
     wiel
    -0.05
     delicately
    -0.05
     but
    -0.05
    POSITIVE LOGITS
     unseren
    0.07
    ردن
    0.07
     your
    0.06
     ಆಯ್
    0.06
     weaning
    0.06
    槃
    0.06
    你的
    0.06
     standalone
    0.06
     usado
    0.06
     ذریع
    0.06
    Activations Density 0.001%

    No Known Activations