© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118838
    Prev
    Next
    INDEX
    Explanations

    published in

    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
     usage
    -0.07
     bumpy
    -0.06
     empathy
    -0.06
     utilizzati
    -0.06
     واست
    -0.06
     any
    -0.06
     realizzato
    -0.06
     wheelchair
    -0.06
    filling
    -0.06
     mythical
    -0.06
    POSITIVE LOGITS
     on
    0.07
    //$
    0.06
     conven
    0.06
     Incre
    0.06
     unequivocal
    0.06
     Receive
    0.06
    ulator
    0.06
    plate
    0.06
     dvara
    0.05
     appreciated
    0.05
    Activations Density 0.001%

    No Known Activations