© 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. 119647
    Prev
    Next
    INDEX
    Explanations

    script tag start

    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
     basic
    -0.06
    jats
    -0.06
    жён
    -0.06
     endeavoured
    -0.06
     coloured
    -0.06
     edged
    -0.06
     an
    -0.06
    和
    -0.06
     coated
    -0.06
     common
    -0.05
    POSITIVE LOGITS
     ending
    0.06
     центру
    0.06
     ব্যর্থ
    0.06
     Successful
    0.06
    ---->
    0.06
     দুটি
    0.06
     séquence
    0.06
    እንደ
    0.06
    Elsewhere
    0.05
    rrrr
    0.05
    Activations Density 0.013%

    No Known Activations