© 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. 117142
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

    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
     adicionales
    -0.06
    fun
    -0.06
     relatifs
    -0.06
    additional
    -0.06
    Run
    -0.06
    igare
    -0.06
    वहीं
    -0.05
     hired
    -0.05
    attached
    -0.05
    খা
    -0.05
    POSITIVE LOGITS
     radically
    0.07
     mimic
    0.07
     mim
    0.06
     национальной
    0.06
     sadness
    0.06
     mimics
    0.06
     vaping
    0.06
     একেবারে
    0.06
     तार
    0.06
     succinct
    0.06
    Activations Density 0.001%

    No Known Activations