© 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. 119922
    Prev
    Next
    INDEX
    Explanations

    analytic derivation and solution

    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
     અથવા
    -0.07
    abela
    -0.06
     options
    -0.06
    밖에
    -0.06
    没什么
    -0.06
     nebo
    -0.06
    നാണ്
    -0.06
    ities
    -0.06
     ಅಥವಾ
    -0.06
    звичай
    -0.06
    POSITIVE LOGITS
     amén
    0.07
     Gelände
    0.06
     Oilers
    0.06
    🌑
    0.06
     parsing
    0.06
     fals
    0.06
    ModuleManager
    0.05
     cartoons
    0.05
     epistem
    0.05
     amplio
    0.05
    Activations Density 0.005%

    No Known Activations