© 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. 119728
    Prev
    Next
    INDEX
    Explanations

    reporting actions

    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
     брен
    -0.08
    Settings
    -0.06
     wajib
    -0.06
    뵌
    -0.06
     laine
    -0.06
     chặn
    -0.06
     vậy
    -0.06
     offered
    -0.06
    提供了
    -0.06
     classed
    -0.06
    POSITIVE LOGITS
     предыду
    0.07
    thinking
    0.05
     объ
    0.05
     consolidating
    0.05
     कोशिश
    0.05
     exhilar
    0.05
     effort
    0.05
    넛
    0.05
     valiant
    0.05
     calculation
    0.05
    Activations Density 0.002%

    No Known Activations