© 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. 120674
    Prev
    Next
    INDEX
    Explanations

    Meadfoot, Ozonation

    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
     these
    -0.08
     چه
    -0.07
     این
    -0.07
     Kinetics
    -0.07
     هذه
    -0.07
     deze
    -0.07
     этих
    -0.06
     può
    -0.06
     estas
    -0.06
     эти
    -0.06
    POSITIVE LOGITS
     usw
    0.06
    お店
    0.06
     у
    0.06
     insists
    0.05
     والس
    0.05
     subdiv
    0.05
     avait
    0.05
    orat
    0.05
    徘
    0.05
     insist
    0.05
    Activations Density 0.001%

    No Known Activations