© 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. 129136
    Prev
    Next
    INDEX
    Explanations

    list items or XML tags

    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
     recently
    -0.08
     Recently
    -0.07
     недавно
    -0.07
     최근
    -0.07
    搜尋
    -0.07
     வீட்டில்
    -0.07
     scorso
    -0.06
     Mulligan
    -0.06
     recientemente
    -0.06
     música
    -0.06
    POSITIVE LOGITS
    ज्ञ
    0.06
     odpowiedzial
    0.06
     দেহ
    0.06
    交给
    0.05
     dovol
    0.05
     one
    0.05
    вичай
    0.05
     accanto
    0.05
     giàu
    0.05
    Other
    0.05
    Activations Density 0.001%

    No Known Activations