© 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. 119651
    Prev
    Next
    INDEX
    Explanations

    free or without

    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
     simplicity
    -0.08
     simplified
    -0.08
     simple
    -0.08
     minimalistic
    -0.08
     minimalist
    -0.08
     simpel
    -0.07
     inexpensive
    -0.07
     simplistic
    -0.07
    simple
    -0.07
     மைய
    -0.07
    POSITIVE LOGITS
    quantum
    0.06
     zonder
    0.06
     অবশ্য
    0.06
    Categ
    0.06
    odos
    0.06
    Mve
    0.06
    without
    0.06
     sized
    0.05
    typen
    0.05
    developed
    0.05
    Activations Density 0.033%

    No Known Activations