© 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. 119255
    Prev
    Next
    INDEX
    Explanations

    basic structure

    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
     changing
    -0.07
    also
    -0.07
    también
    -0.06
     sharing
    -0.06
     also
    -0.06
     shared
    -0.06
     weighty
    -0.06
     metros
    -0.05
     therefore
    -0.05
    ዎች
    -0.05
    POSITIVE LOGITS
    ठान
    0.07
    に含ま
    0.06
     포함
    0.06
     obtenue
    0.06
     цін
    0.06
     verbessert
    0.06
    含
    0.06
     δυνατό
    0.06
     вперед
    0.06
     پیدا
    0.06
    Activations Density 0.001%

    No Known Activations