© 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. 116545
    Prev
    Next
    INDEX
    Explanations

    photo of people and places

    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
     आज
    -0.07
     is
    -0.07
    ı
    -0.06
     mundial
    -0.06
     ఇప్పుడు
    -0.06
    其實
    -0.06
    雖然
    -0.06
     ಈಗ
    -0.06
    るのは
    -0.06
    其实
    -0.06
    POSITIVE LOGITS
    aito
    0.07
    __
    0.06
    ूम
    0.06
     elas
    0.06
     vicinity
    0.06
    AUX
    0.06
     その他
    0.06
     giurid
    0.06
     tandis
    0.06
     жесто
    0.06
    Activations Density 0.003%

    No Known Activations