© 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. 116620
    Prev
    Next
    INDEX
    Explanations

    names preceding legal roles

    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
    及其
    -0.06
     एवं
    -0.06
     hypothesized
    -0.06
     hypothes
    -0.05
    暨
    -0.05
     તથા
    -0.05
    ah
    -0.05
    及び
    -0.05
     últimas
    -0.05
     широко
    -0.05
    POSITIVE LOGITS
    According
    0.07
     ikke
    0.07
     had
    0.07
     When
    0.07
     selon
    0.07
     According
    0.07
    沒有
    0.07
    They
    0.07
     khi
    0.06
     trzy
    0.06
    Activations Density 0.006%

    No Known Activations