© 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. 116565
    Prev
    Next
    INDEX
    Explanations

    using the desktop

    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
     considere
    -0.06
     considers
    -0.06
    Nope
    -0.06
     schaffen
    -0.06
    Boy
    -0.06
    તો
    -0.06
    まさに
    -0.06
    単品
    -0.06
     requires
    -0.06
     battled
    -0.06
    POSITIVE LOGITS
     IMPORTANT
    0.07
    一会儿
    0.07
     реак
    0.07
     benutzen
    0.07
     veces
    0.07
    ometimes
    0.06
     powin
    0.06
    应该
    0.06
     pertama
    0.06
     Use
    0.06
    Activations Density 0.020%

    No Known Activations